diff --git a/Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml b/Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml
index b820c56..855aa08 100644
--- a/Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml
+++ b/Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml
@@ -14,7 +14,12 @@ allOf:
 
 properties:
   compatible:
-    const: airoha,en7581-snand
+    oneOf:
+      - const: airoha,en7581-snand
+      - items:
+          - enum:
+              - airoha,en7523-snand
+          - const: airoha,en7581-snand
 
   reg:
     items:
diff --git a/Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml b/Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml
index 57d932a..80e5426 100644
--- a/Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml
+++ b/Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml
@@ -12,7 +12,7 @@ maintainers:
 
 description: |
   This binding describes the Aspeed Static Memory Controllers (FMC and
-  SPI) of the AST2400, AST2500 and AST2600 SOCs.
+  SPI) of the AST2400, AST2500, AST2600 and AST2700 SOCs.
 
 allOf:
   - $ref: spi-controller.yaml#
@@ -20,6 +20,8 @@ allOf:
 properties:
   compatible:
     enum:
+      - aspeed,ast2700-fmc
+      - aspeed,ast2700-spi
       - aspeed,ast2600-fmc
       - aspeed,ast2600-spi
       - aspeed,ast2500-fmc
diff --git a/Documentation/devicetree/bindings/spi/fsl,spi-fsl-qspi.yaml b/Documentation/devicetree/bindings/spi/fsl,spi-fsl-qspi.yaml
index f2dd203..1d10cfb 100644
--- a/Documentation/devicetree/bindings/spi/fsl,spi-fsl-qspi.yaml
+++ b/Documentation/devicetree/bindings/spi/fsl,spi-fsl-qspi.yaml
@@ -9,9 +9,6 @@ title: Freescale Quad Serial Peripheral Interface (QuadSPI)
 maintainers:
   - Han Xu <han.xu@nxp.com>
 
-allOf:
-  - $ref: spi-controller.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -22,6 +19,7 @@ properties:
           - fsl,imx6ul-qspi
           - fsl,ls1021a-qspi
           - fsl,ls2080a-qspi
+          - spacemit,k1-qspi
       - items:
           - enum:
               - fsl,ls1043a-qspi
@@ -54,6 +52,11 @@ properties:
       - const: qspi_en
       - const: qspi
 
+  resets:
+    items:
+      - description: SoC QSPI reset
+      - description: SoC QSPI bus reset
+
 required:
   - compatible
   - reg
@@ -62,6 +65,18 @@ required:
   - clocks
   - clock-names
 
+allOf:
+  - $ref: spi-controller.yaml#
+  - if:
+      properties:
+        compatible:
+          not:
+            contains:
+              const: spacemit,k1-qspi
+    then:
+      properties:
+        resets: false
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml b/Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml
index 62a568b..636338d 100644
--- a/Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml
@@ -21,11 +21,13 @@ properties:
               - microchip,mpfs-qspi
               - microchip,pic64gx-qspi
           - const: microchip,coreqspi-rtl-v2
-      - const: microchip,coreqspi-rtl-v2 # FPGA QSPI
+      - enum:
+          - microchip,coreqspi-rtl-v2 # FPGA QSPI
+          - microchip,corespi-rtl-v5 # FPGA CoreSPI
+          - microchip,mpfs-spi
       - items:
           - const: microchip,pic64gx-spi
           - const: microchip,mpfs-spi
-      - const: microchip,mpfs-spi
 
   reg:
     maxItems: 1
@@ -39,6 +41,45 @@ properties:
   clocks:
     maxItems: 1
 
+  microchip,apb-datawidth:
+    description: APB bus data width in bits.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [8, 16, 32]
+    default: 8
+
+  microchip,frame-size:
+    description: |
+      Number of bits per SPI frame, as configured in Libero.
+      In Motorola and TI modes, this corresponds directly
+      to the requested frame size. For NSC mode this is set
+      to 9 + the required data frame size.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 4
+    maximum: 32
+    default: 8
+
+  microchip,protocol-configuration:
+    description: CoreSPI protocol selection. Determines operating mode
+    $ref: /schemas/types.yaml#/definitions/string
+    enum:
+      - motorola
+      - ti
+      - nsc
+    default: motorola
+
+  microchip,motorola-mode:
+    description: Motorola SPI mode selection
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [0, 1, 2, 3]
+    default: 3
+
+  microchip,ssel-active:
+    description: |
+      Keep SSEL asserted between frames when using the Motorola protocol.
+      When present, the controller keeps SSEL active across contiguous
+      transfers and deasserts only when the overall transfer completes.
+    type: boolean
+
 required:
   - compatible
   - reg
@@ -71,6 +112,31 @@ allOf:
         num-cs:
           maximum: 1
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: microchip,corespi-rtl-v5
+    then:
+      properties:
+        num-cs:
+          minimum: 1
+          maximum: 8
+          default: 8
+
+        fifo-depth:
+          minimum: 1
+          maximum: 32
+          default: 4
+
+    else:
+      properties:
+        microchip,apb-datawidth: false
+        microchip,frame-size: false
+        microchip,protocol-configuration: false
+        microchip,motorola-mode: false
+        microchip,ssel-active: false
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/spi/nuvoton,npcm-pspi.txt b/Documentation/devicetree/bindings/spi/nuvoton,npcm-pspi.txt
deleted file mode 100644
index a4e72e5..0000000
--- a/Documentation/devicetree/bindings/spi/nuvoton,npcm-pspi.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-Nuvoton NPCM Peripheral Serial Peripheral Interface(PSPI) controller driver
-
-Nuvoton NPCM7xx SOC support two PSPI channels.
-
-Required properties:
- - compatible : "nuvoton,npcm750-pspi" for Poleg NPCM7XX.
-				"nuvoton,npcm845-pspi" for Arbel NPCM8XX.
- - #address-cells : should be 1. see spi-bus.txt
- - #size-cells : should be 0. see spi-bus.txt
- - specifies physical base address and size of the register.
- - interrupts : contain PSPI interrupt.
- - clocks : phandle of PSPI reference clock.
- - clock-names: Should be "clk_apb5".
- - pinctrl-names : a pinctrl state named "default" must be defined.
- - pinctrl-0 : phandle referencing pin configuration of the device.
- - resets : phandle to the reset control for this device.
- - cs-gpios: Specifies the gpio pins to be used for chipselects.
-            See: Documentation/devicetree/bindings/spi/spi-bus.txt
-
-Optional properties:
-- clock-frequency : Input clock frequency to the PSPI block in Hz.
-		    Default is 25000000 Hz.
-
-spi0: spi@f0200000 {
-	compatible = "nuvoton,npcm750-pspi";
-	reg = <0xf0200000 0x1000>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&pspi1_pins>;
-	#address-cells = <1>;
-	#size-cells = <0>;
-	interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
-	clocks = <&clk NPCM7XX_CLK_APB5>;
-	clock-names = "clk_apb5";
-	resets = <&rstc NPCM7XX_RESET_IPSRST2 NPCM7XX_RESET_PSPI1>
-	cs-gpios = <&gpio6 11 GPIO_ACTIVE_LOW>;
-};
diff --git a/Documentation/devicetree/bindings/spi/nuvoton,npcm-pspi.yaml b/Documentation/devicetree/bindings/spi/nuvoton,npcm-pspi.yaml
new file mode 100644
index 0000000..db0fb87
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/nuvoton,npcm-pspi.yaml
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/nuvoton,npcm-pspi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Nuvoton NPCM Peripheral SPI (PSPI) Controller
+
+maintainers:
+  - Tomer Maimon <tmaimon77@gmail.com>
+
+allOf:
+  - $ref: spi-controller.yaml#
+
+description:
+  Nuvoton NPCM Peripheral Serial Peripheral Interface (PSPI) controller.
+  Nuvoton NPCM7xx SOC supports two PSPI channels.
+  Nuvoton NPCM8xx SOC support one PSPI channel.
+
+properties:
+  compatible:
+    enum:
+      - nuvoton,npcm750-pspi # Poleg NPCM7XX
+      - nuvoton,npcm845-pspi # Arbel NPCM8XX
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+    description: PSPI reference clock.
+
+  clock-names:
+    items:
+      - const: clk_apb5
+
+  resets:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/nuvoton,npcm7xx-clock.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/reset/nuvoton,npcm7xx-reset.h>
+    #include "dt-bindings/gpio/gpio.h"
+    spi0: spi@f0200000 {
+        compatible = "nuvoton,npcm750-pspi";
+        reg = <0xf0200000 0x1000>;
+        pinctrl-names = "default";
+        pinctrl-0 = <&pspi1_pins>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+        interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&clk NPCM7XX_CLK_APB5>;
+        clock-names = "clk_apb5";
+        resets = <&rstc NPCM7XX_RESET_IPSRST2 NPCM7XX_RESET_PSPI1>;
+        cs-gpios = <&gpio6 11 GPIO_ACTIVE_LOW>;
+    };
+
diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-qpic-snand.yaml b/Documentation/devicetree/bindings/spi/qcom,spi-qpic-snand.yaml
index cb1f152..7d0571f 100644
--- a/Documentation/devicetree/bindings/spi/qcom,spi-qpic-snand.yaml
+++ b/Documentation/devicetree/bindings/spi/qcom,spi-qpic-snand.yaml
@@ -25,6 +25,8 @@ properties:
       - items:
           - enum:
               - qcom,ipq5018-snand
+              - qcom,ipq5332-snand
+              - qcom,ipq5424-snand
           - const: qcom,ipq9574-snand
       - const: qcom,ipq9574-snand
 
diff --git a/Documentation/devicetree/bindings/spi/renesas,rzv2h-rspi.yaml b/Documentation/devicetree/bindings/spi/renesas,rzv2h-rspi.yaml
index ab27fef..069557a 100644
--- a/Documentation/devicetree/bindings/spi/renesas,rzv2h-rspi.yaml
+++ b/Documentation/devicetree/bindings/spi/renesas,rzv2h-rspi.yaml
@@ -9,12 +9,18 @@ title: Renesas RZ/V2H(P) Renesas Serial Peripheral Interface (RSPI)
 maintainers:
   - Fabrizio Castro <fabrizio.castro.jz@renesas.com>
 
-allOf:
-  - $ref: spi-controller.yaml#
-
 properties:
   compatible:
-    const: renesas,r9a09g057-rspi # RZ/V2H(P)
+    oneOf:
+      - enum:
+          - renesas,r9a09g057-rspi # RZ/V2H(P)
+          - renesas,r9a09g077-rspi # RZ/T2H
+      - items:
+          - const: renesas,r9a09g056-rspi # RZ/V2N
+          - const: renesas,r9a09g057-rspi
+      - items:
+          - const: renesas,r9a09g087-rspi # RZ/N2H
+          - const: renesas,r9a09g077-rspi # RZ/T2H
 
   reg:
     maxItems: 1
@@ -36,13 +42,12 @@ properties:
       - const: tx
 
   clocks:
+    minItems: 2
     maxItems: 3
 
   clock-names:
-    items:
-      - const: pclk
-      - const: pclk_sfr
-      - const: tclk
+    minItems: 2
+    maxItems: 3
 
   resets:
     maxItems: 2
@@ -62,12 +67,52 @@ required:
   - interrupt-names
   - clocks
   - clock-names
-  - resets
-  - reset-names
   - power-domains
   - '#address-cells'
   - '#size-cells'
 
+allOf:
+  - $ref: spi-controller.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,r9a09g057-rspi
+    then:
+      properties:
+        clocks:
+          minItems: 3
+
+        clock-names:
+          items:
+            - const: pclk
+            - const: pclk_sfr
+            - const: tclk
+
+      required:
+        - resets
+        - reset-names
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,r9a09g077-rspi
+    then:
+      properties:
+        clocks:
+          maxItems: 2
+
+        clock-names:
+          items:
+            - const: pclk
+            - const: pclkspi
+
+        resets: false
+        reset-names: false
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index 0543c52..5c87fc8 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -153,7 +153,7 @@ properties:
       provides an interface to override the native DWC SSI CS control.
 
 patternProperties:
-  "^.*@[0-9a-f]+$":
+  "@[0-9a-f]+$":
     type: object
     additionalProperties: true
 
diff --git a/Documentation/devicetree/bindings/spi/spi-cadence.yaml b/Documentation/devicetree/bindings/spi/spi-cadence.yaml
index 27414b7..347bed0 100644
--- a/Documentation/devicetree/bindings/spi/spi-cadence.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-cadence.yaml
@@ -21,6 +21,7 @@ properties:
           - enum:
               - xlnx,zynqmp-spi-r1p6
               - xlnx,versal-net-spi-r1p6
+              - cix,sky1-spi-r1p6
           - const: cdns,spi-r1p6
 
   reg:
diff --git a/Documentation/devicetree/bindings/spi/spi-controller.yaml b/Documentation/devicetree/bindings/spi/spi-controller.yaml
index 82d051f..3b8e990 100644
--- a/Documentation/devicetree/bindings/spi/spi-controller.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-controller.yaml
@@ -111,7 +111,7 @@ properties:
       - compatible
 
 patternProperties:
-  "^.*@[0-9a-f]+$":
+  "@[0-9a-f]+$":
     type: object
     $ref: spi-peripheral-props.yaml
     additionalProperties: true
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 58ff948..9bff5f0 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -53,6 +53,8 @@ properties:
           - adi,lt7182s
             # AMS iAQ-Core VOC Sensor
           - ams,iaq-core
+            # Arduino microcontroller interface over SPI on UnoQ board
+          - arduino,unoq-mcu
             # Temperature monitoring of Astera Labs PT5161L PCIe retimer
           - asteralabs,pt5161l
             # i2c h/w elliptic curve crypto module
diff --git a/MAINTAINERS b/MAINTAINERS
index fb8d62f..71afc62 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22247,7 +22247,7 @@ F:	drivers/reset/reset-mpfs.c
 F:	drivers/rtc/rtc-mpfs.c
 F:	drivers/soc/microchip/mpfs-sys-controller.c
 F:	drivers/spi/spi-microchip-core-qspi.c
-F:	drivers/spi/spi-microchip-core.c
+F:	drivers/spi/spi-mpfs.c
 F:	drivers/usb/musb/mpfs.c
 F:	include/soc/microchip/mpfs.h
 
@@ -24385,6 +24385,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi.git
 F:	Documentation/devicetree/bindings/spi/
 F:	Documentation/spi/
 F:	drivers/spi/
+F:	include/trace/events/spi*
 F:	include/linux/spi/
 F:	include/uapi/linux/spi/
 F:	tools/spi/
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 5567575..5520403 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -435,7 +435,8 @@ config SPI_FSL_LPSPI
 
 config SPI_FSL_QUADSPI
 	tristate "Freescale QSPI controller"
-	depends on ARCH_MXC || SOC_LS1021A || ARCH_LAYERSCAPE || COMPILE_TEST
+	depends on ARCH_MXC || SOC_LS1021A || ARCH_LAYERSCAPE || \
+		   ARCH_SPACEMIT || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
 	  This enables support for the Quad SPI controller in master mode.
@@ -706,15 +707,6 @@ config SPI_MESON_SPIFC
 	  This enables master mode support for the SPIFC (SPI flash
 	  controller) available in Amlogic Meson SoCs.
 
-config SPI_MICROCHIP_CORE
-	tristate "Microchip FPGA SPI controllers"
-	depends on SPI_MASTER
-	help
-	  This enables the SPI driver for Microchip FPGA SPI controllers.
-	  Say Y or M here if you want to use the "hard" controllers on
-	  PolarFire SoC.
-	  If built as a module, it will be called spi-microchip-core.
-
 config SPI_MICROCHIP_CORE_QSPI
 	tristate "Microchip FPGA QSPI controllers"
 	depends on SPI_MASTER
@@ -724,6 +716,15 @@ config SPI_MICROCHIP_CORE_QSPI
 	  PolarFire SoC.
 	  If built as a module, it will be called spi-microchip-core-qspi.
 
+config SPI_MICROCHIP_CORE_SPI
+	tristate "Microchip FPGA CoreSPI controller"
+	depends on SPI_MASTER
+	help
+	  This enables the SPI driver for Microchip FPGA CoreSPI controller.
+	  Say Y or M here if you want to use the "soft" controllers on
+	  PolarFire SoC.
+	  If built as a module, it will be called spi-microchip-core-spi.
+
 config SPI_MT65XX
 	tristate "MediaTek SPI controller"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
@@ -871,6 +872,16 @@ config SPI_PL022
 	  controller. If you have an embedded system with an AMBA(R)
 	  bus and a PL022 controller, say Y or M here.
 
+config SPI_POLARFIRE_SOC
+	tristate "Microchip FPGA SPI controllers"
+	depends on SPI_MASTER
+	depends on ARCH_MICROCHIP || COMPILE_TEST
+	help
+	  This enables the SPI driver for Microchip FPGA SPI controllers.
+	  Say Y or M here if you want to use the "hard" controllers on
+	  PolarFire SoC.
+	  If built as a module, it will be called spi-mpfs.
+
 config SPI_PPC4xx
 	tristate "PPC4xx SPI Controller"
 	depends on PPC32 && 4xx
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 8ff74a1..863b628 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -86,8 +86,8 @@ obj-$(CONFIG_SPI_LOONGSON_PLATFORM)	+= spi-loongson-plat.o
 obj-$(CONFIG_SPI_LP8841_RTC)		+= spi-lp8841-rtc.o
 obj-$(CONFIG_SPI_MESON_SPICC)		+= spi-meson-spicc.o
 obj-$(CONFIG_SPI_MESON_SPIFC)		+= spi-meson-spifc.o
-obj-$(CONFIG_SPI_MICROCHIP_CORE)	+= spi-microchip-core.o
 obj-$(CONFIG_SPI_MICROCHIP_CORE_QSPI)	+= spi-microchip-core-qspi.o
+obj-$(CONFIG_SPI_MICROCHIP_CORE_SPI)	+= spi-microchip-core-spi.o
 obj-$(CONFIG_SPI_MPC512x_PSC)		+= spi-mpc512x-psc.o
 obj-$(CONFIG_SPI_MPC52xx_PSC)		+= spi-mpc52xx-psc.o
 obj-$(CONFIG_SPI_MPC52xx)		+= spi-mpc52xx.o
@@ -97,6 +97,7 @@ obj-$(CONFIG_SPI_MTK_NOR)		+= spi-mtk-nor.o
 obj-$(CONFIG_SPI_MTK_SNFI)		+= spi-mtk-snfi.o
 obj-$(CONFIG_SPI_MXIC)			+= spi-mxic.o
 obj-$(CONFIG_SPI_MXS)			+= spi-mxs.o
+obj-$(CONFIG_SPI_POLARFIRE_SOC)		+= spi-mpfs.o
 obj-$(CONFIG_SPI_WPCM_FIU)		+= spi-wpcm-fiu.o
 obj-$(CONFIG_SPI_NPCM_FIU)		+= spi-npcm-fiu.o
 obj-$(CONFIG_SPI_NPCM_PSPI)		+= spi-npcm-pspi.o
diff --git a/drivers/spi/spi-airoha-snfi.c b/drivers/spi/spi-airoha-snfi.c
index b78163e..70327ae 100644
--- a/drivers/spi/spi-airoha-snfi.c
+++ b/drivers/spi/spi-airoha-snfi.c
@@ -147,6 +147,8 @@
 #define SPI_NFI_CUS_SEC_SIZE_EN			BIT(16)
 
 #define REG_SPI_NFI_RD_CTL2			0x0510
+#define SPI_NFI_DATA_READ_CMD			GENMASK(7, 0)
+
 #define REG_SPI_NFI_RD_CTL3			0x0514
 
 #define REG_SPI_NFI_PG_CTL1			0x0524
@@ -179,7 +181,9 @@
 #define SPI_NAND_OP_READ_FROM_CACHE_SINGLE	0x03
 #define SPI_NAND_OP_READ_FROM_CACHE_SINGLE_FAST	0x0b
 #define SPI_NAND_OP_READ_FROM_CACHE_DUAL	0x3b
+#define SPI_NAND_OP_READ_FROM_CACHE_DUALIO	0xbb
 #define SPI_NAND_OP_READ_FROM_CACHE_QUAD	0x6b
+#define SPI_NAND_OP_READ_FROM_CACHE_QUADIO	0xeb
 #define SPI_NAND_OP_WRITE_ENABLE		0x06
 #define SPI_NAND_OP_WRITE_DISABLE		0x04
 #define SPI_NAND_OP_PROGRAM_LOAD_SINGLE		0x02
@@ -219,13 +223,6 @@ struct airoha_snand_ctrl {
 	struct regmap *regmap_ctrl;
 	struct regmap *regmap_nfi;
 	struct clk *spi_clk;
-
-	struct {
-		size_t page_size;
-		size_t sec_size;
-		u8 sec_num;
-		u8 spare_size;
-	} nfi_cfg;
 };
 
 static int airoha_snand_set_fifo_op(struct airoha_snand_ctrl *as_ctrl,
@@ -486,92 +483,6 @@ static int airoha_snand_nfi_init(struct airoha_snand_ctrl *as_ctrl)
 				  SPI_NFI_ALL_IRQ_EN, SPI_NFI_AHB_DONE_EN);
 }
 
-static int airoha_snand_nfi_config(struct airoha_snand_ctrl *as_ctrl)
-{
-	int err;
-	u32 val;
-
-	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
-			   SPI_NFI_FIFO_FLUSH | SPI_NFI_RST);
-	if (err)
-		return err;
-
-	/* auto FDM */
-	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
-				SPI_NFI_AUTO_FDM_EN);
-	if (err)
-		return err;
-
-	/* HW ECC */
-	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
-				SPI_NFI_HW_ECC_EN);
-	if (err)
-		return err;
-
-	/* DMA Burst */
-	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
-			      SPI_NFI_DMA_BURST_EN);
-	if (err)
-		return err;
-
-	/* page format */
-	switch (as_ctrl->nfi_cfg.spare_size) {
-	case 26:
-		val = FIELD_PREP(SPI_NFI_SPARE_SIZE, 0x1);
-		break;
-	case 27:
-		val = FIELD_PREP(SPI_NFI_SPARE_SIZE, 0x2);
-		break;
-	case 28:
-		val = FIELD_PREP(SPI_NFI_SPARE_SIZE, 0x3);
-		break;
-	default:
-		val = FIELD_PREP(SPI_NFI_SPARE_SIZE, 0x0);
-		break;
-	}
-
-	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_PAGEFMT,
-				 SPI_NFI_SPARE_SIZE, val);
-	if (err)
-		return err;
-
-	switch (as_ctrl->nfi_cfg.page_size) {
-	case 2048:
-		val = FIELD_PREP(SPI_NFI_PAGE_SIZE, 0x1);
-		break;
-	case 4096:
-		val = FIELD_PREP(SPI_NFI_PAGE_SIZE, 0x2);
-		break;
-	default:
-		val = FIELD_PREP(SPI_NFI_PAGE_SIZE, 0x0);
-		break;
-	}
-
-	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_PAGEFMT,
-				 SPI_NFI_PAGE_SIZE, val);
-	if (err)
-		return err;
-
-	/* sec num */
-	val = FIELD_PREP(SPI_NFI_SEC_NUM, as_ctrl->nfi_cfg.sec_num);
-	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
-				 SPI_NFI_SEC_NUM, val);
-	if (err)
-		return err;
-
-	/* enable cust sec size */
-	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SECCUS_SIZE,
-			      SPI_NFI_CUS_SEC_SIZE_EN);
-	if (err)
-		return err;
-
-	/* set cust sec size */
-	val = FIELD_PREP(SPI_NFI_CUS_SEC_SIZE, as_ctrl->nfi_cfg.sec_size);
-	return regmap_update_bits(as_ctrl->regmap_nfi,
-				  REG_SPI_NFI_SECCUS_SIZE,
-				  SPI_NFI_CUS_SEC_SIZE, val);
-}
-
 static bool airoha_snand_is_page_ops(const struct spi_mem_op *op)
 {
 	if (op->addr.nbytes != 2)
@@ -604,33 +515,6 @@ static bool airoha_snand_is_page_ops(const struct spi_mem_op *op)
 	}
 }
 
-static int airoha_snand_adjust_op_size(struct spi_mem *mem,
-				       struct spi_mem_op *op)
-{
-	size_t max_len;
-
-	if (airoha_snand_is_page_ops(op)) {
-		struct airoha_snand_ctrl *as_ctrl;
-
-		as_ctrl = spi_controller_get_devdata(mem->spi->controller);
-		max_len = as_ctrl->nfi_cfg.sec_size;
-		max_len += as_ctrl->nfi_cfg.spare_size;
-		max_len *= as_ctrl->nfi_cfg.sec_num;
-
-		if (op->data.nbytes > max_len)
-			op->data.nbytes = max_len;
-	} else {
-		max_len = 1 + op->addr.nbytes + op->dummy.nbytes;
-		if (max_len >= 160)
-			return -EOPNOTSUPP;
-
-		if (op->data.nbytes > 160 - max_len)
-			op->data.nbytes = 160 - max_len;
-	}
-
-	return 0;
-}
-
 static bool airoha_snand_supports_op(struct spi_mem *mem,
 				     const struct spi_mem_op *op)
 {
@@ -671,32 +555,89 @@ static int airoha_snand_dirmap_create(struct spi_mem_dirmap_desc *desc)
 static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc,
 					u64 offs, size_t len, void *buf)
 {
-	struct spi_mem_op *op = &desc->info.op_tmpl;
 	struct spi_device *spi = desc->mem->spi;
 	struct airoha_snand_ctrl *as_ctrl;
 	u8 *txrx_buf = spi_get_ctldata(spi);
 	dma_addr_t dma_addr;
-	u32 val, rd_mode;
+	u32 val, rd_mode, opcode;
+	size_t bytes;
 	int err;
 
-	switch (op->cmd.opcode) {
+	as_ctrl = spi_controller_get_devdata(spi->controller);
+
+	/* minimum oob size is 64 */
+	bytes = round_up(offs + len, 64);
+
+	/*
+	 * DUALIO and QUADIO opcodes are not supported by the spi controller,
+	 * replace them with supported opcodes.
+	 */
+	opcode = desc->info.op_tmpl.cmd.opcode;
+	switch (opcode) {
+	case SPI_NAND_OP_READ_FROM_CACHE_SINGLE:
+	case SPI_NAND_OP_READ_FROM_CACHE_SINGLE_FAST:
+		rd_mode = 0;
+		break;
 	case SPI_NAND_OP_READ_FROM_CACHE_DUAL:
+	case SPI_NAND_OP_READ_FROM_CACHE_DUALIO:
+		opcode = SPI_NAND_OP_READ_FROM_CACHE_DUAL;
 		rd_mode = 1;
 		break;
 	case SPI_NAND_OP_READ_FROM_CACHE_QUAD:
+	case SPI_NAND_OP_READ_FROM_CACHE_QUADIO:
+		opcode = SPI_NAND_OP_READ_FROM_CACHE_QUAD;
 		rd_mode = 2;
 		break;
 	default:
-		rd_mode = 0;
-		break;
+		/* unknown opcode */
+		return -EOPNOTSUPP;
 	}
 
-	as_ctrl = spi_controller_get_devdata(spi->controller);
 	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_DMA);
 	if (err < 0)
 		return err;
 
-	err = airoha_snand_nfi_config(as_ctrl);
+	/* NFI reset */
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+			   SPI_NFI_FIFO_FLUSH | SPI_NFI_RST);
+	if (err)
+		goto error_dma_mode_off;
+
+	/* NFI configure:
+	 *   - No AutoFDM (custom sector size (SECCUS) register will be used)
+	 *   - No SoC's hardware ECC (flash internal ECC will be used)
+	 *   - Use burst mode (faster, but requires 16 byte alignment for addresses)
+	 *   - Setup for reading (SPI_NFI_READ_MODE)
+	 *   - Setup reading command: FIELD_PREP(SPI_NFI_OPMODE, 6)
+	 *   - Use DMA instead of PIO for data reading
+	 */
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+				 SPI_NFI_DMA_MODE |
+				 SPI_NFI_READ_MODE |
+				 SPI_NFI_DMA_BURST_EN |
+				 SPI_NFI_HW_ECC_EN |
+				 SPI_NFI_AUTO_FDM_EN |
+				 SPI_NFI_OPMODE,
+				 SPI_NFI_DMA_MODE |
+				 SPI_NFI_READ_MODE |
+				 SPI_NFI_DMA_BURST_EN |
+				 FIELD_PREP(SPI_NFI_OPMODE, 6));
+	if (err)
+		goto error_dma_mode_off;
+
+	/* Set number of sector will be read */
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+				 SPI_NFI_SEC_NUM,
+				 FIELD_PREP(SPI_NFI_SEC_NUM, 1));
+	if (err)
+		goto error_dma_mode_off;
+
+	/* Set custom sector size */
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SECCUS_SIZE,
+				 SPI_NFI_CUS_SEC_SIZE |
+				 SPI_NFI_CUS_SEC_SIZE_EN,
+				 FIELD_PREP(SPI_NFI_CUS_SEC_SIZE, bytes) |
+				 SPI_NFI_CUS_SEC_SIZE_EN);
 	if (err)
 		goto error_dma_mode_off;
 
@@ -712,18 +653,24 @@ static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc,
 	if (err)
 		goto error_dma_unmap;
 
-	/* set cust sec size */
-	val = as_ctrl->nfi_cfg.sec_size * as_ctrl->nfi_cfg.sec_num;
-	val = FIELD_PREP(SPI_NFI_READ_DATA_BYTE_NUM, val);
+	/*
+	 * Setup transfer length
+	 * ---------------------
+	 * The following rule MUST be met:
+	 *     transfer_length =
+	 *        = NFI_SNF_MISC_CTL2.read_data_byte_number =
+	 *        = NFI_CON.sector_number * NFI_SECCUS.custom_sector_size
+	 */
 	err = regmap_update_bits(as_ctrl->regmap_nfi,
 				 REG_SPI_NFI_SNF_MISC_CTL2,
-				 SPI_NFI_READ_DATA_BYTE_NUM, val);
+				 SPI_NFI_READ_DATA_BYTE_NUM,
+				 FIELD_PREP(SPI_NFI_READ_DATA_BYTE_NUM, bytes));
 	if (err)
 		goto error_dma_unmap;
 
 	/* set read command */
 	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_RD_CTL2,
-			   op->cmd.opcode);
+			   FIELD_PREP(SPI_NFI_DATA_READ_CMD, opcode));
 	if (err)
 		goto error_dma_unmap;
 
@@ -739,23 +686,11 @@ static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc,
 	if (err)
 		goto error_dma_unmap;
 
-	/* set nfi read */
-	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
-				 SPI_NFI_OPMODE,
-				 FIELD_PREP(SPI_NFI_OPMODE, 6));
-	if (err)
-		goto error_dma_unmap;
-
-	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
-			      SPI_NFI_READ_MODE | SPI_NFI_DMA_MODE);
-	if (err)
-		goto error_dma_unmap;
-
 	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_CMD, 0x0);
 	if (err)
 		goto error_dma_unmap;
 
-	/* trigger dma start read */
+	/* trigger dma reading */
 	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
 				SPI_NFI_RD_TRIG);
 	if (err)
@@ -813,59 +748,122 @@ error_dma_mode_off:
 static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc,
 					 u64 offs, size_t len, const void *buf)
 {
-	struct spi_mem_op *op = &desc->info.op_tmpl;
 	struct spi_device *spi = desc->mem->spi;
 	u8 *txrx_buf = spi_get_ctldata(spi);
 	struct airoha_snand_ctrl *as_ctrl;
 	dma_addr_t dma_addr;
-	u32 wr_mode, val;
+	u32 wr_mode, val, opcode;
+	size_t bytes;
 	int err;
 
 	as_ctrl = spi_controller_get_devdata(spi->controller);
-	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL);
-	if (err < 0)
-		return err;
 
+	/* minimum oob size is 64 */
+	bytes = round_up(offs + len, 64);
+
+	opcode = desc->info.op_tmpl.cmd.opcode;
+	switch (opcode) {
+	case SPI_NAND_OP_PROGRAM_LOAD_SINGLE:
+	case SPI_NAND_OP_PROGRAM_LOAD_RAMDOM_SINGLE:
+		wr_mode = 0;
+		break;
+	case SPI_NAND_OP_PROGRAM_LOAD_QUAD:
+	case SPI_NAND_OP_PROGRAM_LOAD_RAMDON_QUAD:
+		wr_mode = 2;
+		break;
+	default:
+		/* unknown opcode */
+		return -EOPNOTSUPP;
+	}
+
+	if (offs > 0)
+		memset(txrx_buf, 0xff, offs);
 	memcpy(txrx_buf + offs, buf, len);
-	dma_addr = dma_map_single(as_ctrl->dev, txrx_buf, SPI_NAND_CACHE_SIZE,
-				  DMA_TO_DEVICE);
-	err = dma_mapping_error(as_ctrl->dev, dma_addr);
-	if (err)
-		return err;
+	if (bytes > offs + len)
+		memset(txrx_buf + offs + len, 0xff, bytes - offs - len);
 
 	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_DMA);
 	if (err < 0)
-		goto error_dma_unmap;
+		return err;
+
+	/* NFI reset */
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+			   SPI_NFI_FIFO_FLUSH | SPI_NFI_RST);
+	if (err)
+		goto error_dma_mode_off;
 
-	err = airoha_snand_nfi_config(as_ctrl);
+	/*
+	 * NFI configure:
+	 *   - No AutoFDM (custom sector size (SECCUS) register will be used)
+	 *   - No SoC's hardware ECC (flash internal ECC will be used)
+	 *   - Use burst mode (faster, but requires 16 byte alignment for addresses)
+	 *   - Setup for writing (SPI_NFI_READ_MODE bit is cleared)
+	 *   - Setup writing command: FIELD_PREP(SPI_NFI_OPMODE, 3)
+	 *   - Use DMA instead of PIO for data writing
+	 */
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+				 SPI_NFI_DMA_MODE |
+				 SPI_NFI_READ_MODE |
+				 SPI_NFI_DMA_BURST_EN |
+				 SPI_NFI_HW_ECC_EN |
+				 SPI_NFI_AUTO_FDM_EN |
+				 SPI_NFI_OPMODE,
+				 SPI_NFI_DMA_MODE |
+				 SPI_NFI_DMA_BURST_EN |
+				 FIELD_PREP(SPI_NFI_OPMODE, 3));
 	if (err)
-		goto error_dma_unmap;
+		goto error_dma_mode_off;
 
-	if (op->cmd.opcode == SPI_NAND_OP_PROGRAM_LOAD_QUAD ||
-	    op->cmd.opcode == SPI_NAND_OP_PROGRAM_LOAD_RAMDON_QUAD)
-		wr_mode = BIT(1);
-	else
-		wr_mode = 0;
+	/* Set number of sector will be written */
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+				 SPI_NFI_SEC_NUM,
+				 FIELD_PREP(SPI_NFI_SEC_NUM, 1));
+	if (err)
+		goto error_dma_mode_off;
+
+	/* Set custom sector size */
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SECCUS_SIZE,
+				 SPI_NFI_CUS_SEC_SIZE |
+				 SPI_NFI_CUS_SEC_SIZE_EN,
+				 FIELD_PREP(SPI_NFI_CUS_SEC_SIZE, bytes) |
+				 SPI_NFI_CUS_SEC_SIZE_EN);
+	if (err)
+		goto error_dma_mode_off;
+
+	dma_addr = dma_map_single(as_ctrl->dev, txrx_buf, SPI_NAND_CACHE_SIZE,
+				  DMA_TO_DEVICE);
+	err = dma_mapping_error(as_ctrl->dev, dma_addr);
+	if (err)
+		goto error_dma_mode_off;
 
+	/* set dma addr */
 	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_STRADDR,
 			   dma_addr);
 	if (err)
 		goto error_dma_unmap;
 
-	val = FIELD_PREP(SPI_NFI_PROG_LOAD_BYTE_NUM,
-			 as_ctrl->nfi_cfg.sec_size * as_ctrl->nfi_cfg.sec_num);
+	/*
+	 * Setup transfer length
+	 * ---------------------
+	 * The following rule MUST be met:
+	 *     transfer_length =
+	 *        = NFI_SNF_MISC_CTL2.write_data_byte_number =
+	 *        = NFI_CON.sector_number * NFI_SECCUS.custom_sector_size
+	 */
 	err = regmap_update_bits(as_ctrl->regmap_nfi,
 				 REG_SPI_NFI_SNF_MISC_CTL2,
-				 SPI_NFI_PROG_LOAD_BYTE_NUM, val);
+				 SPI_NFI_PROG_LOAD_BYTE_NUM,
+				 FIELD_PREP(SPI_NFI_PROG_LOAD_BYTE_NUM, bytes));
 	if (err)
 		goto error_dma_unmap;
 
+	/* set write command */
 	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_PG_CTL1,
-			   FIELD_PREP(SPI_NFI_PG_LOAD_CMD,
-				      op->cmd.opcode));
+			   FIELD_PREP(SPI_NFI_PG_LOAD_CMD, opcode));
 	if (err)
 		goto error_dma_unmap;
 
+	/* set write mode */
 	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_MISC_CTL,
 			   FIELD_PREP(SPI_NFI_DATA_READ_WR_MODE, wr_mode));
 	if (err)
@@ -877,26 +875,11 @@ static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc,
 	if (err)
 		goto error_dma_unmap;
 
-	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
-				SPI_NFI_READ_MODE);
-	if (err)
-		goto error_dma_unmap;
-
-	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
-				 SPI_NFI_OPMODE,
-				 FIELD_PREP(SPI_NFI_OPMODE, 3));
-	if (err)
-		goto error_dma_unmap;
-
-	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
-			      SPI_NFI_DMA_MODE);
-	if (err)
-		goto error_dma_unmap;
-
 	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_CMD, 0x80);
 	if (err)
 		goto error_dma_unmap;
 
+	/* trigger dma writing */
 	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
 				SPI_NFI_WR_TRIG);
 	if (err)
@@ -941,6 +924,7 @@ static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc,
 error_dma_unmap:
 	dma_unmap_single(as_ctrl->dev, dma_addr, SPI_NAND_CACHE_SIZE,
 			 DMA_TO_DEVICE);
+error_dma_mode_off:
 	airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL);
 	return err;
 }
@@ -1022,7 +1006,6 @@ static int airoha_snand_exec_op(struct spi_mem *mem,
 }
 
 static const struct spi_controller_mem_ops airoha_snand_mem_ops = {
-	.adjust_op_size = airoha_snand_adjust_op_size,
 	.supports_op = airoha_snand_supports_op,
 	.exec_op = airoha_snand_exec_op,
 	.dirmap_create = airoha_snand_dirmap_create,
@@ -1030,6 +1013,11 @@ static const struct spi_controller_mem_ops airoha_snand_mem_ops = {
 	.dirmap_write = airoha_snand_dirmap_write,
 };
 
+static const struct spi_controller_mem_ops airoha_snand_nodma_mem_ops = {
+	.supports_op = airoha_snand_supports_op,
+	.exec_op = airoha_snand_exec_op,
+};
+
 static int airoha_snand_setup(struct spi_device *spi)
 {
 	struct airoha_snand_ctrl *as_ctrl;
@@ -1047,36 +1035,6 @@ static int airoha_snand_setup(struct spi_device *spi)
 	return 0;
 }
 
-static int airoha_snand_nfi_setup(struct airoha_snand_ctrl *as_ctrl)
-{
-	u32 val, sec_size, sec_num;
-	int err;
-
-	err = regmap_read(as_ctrl->regmap_nfi, REG_SPI_NFI_CON, &val);
-	if (err)
-		return err;
-
-	sec_num = FIELD_GET(SPI_NFI_SEC_NUM, val);
-
-	err = regmap_read(as_ctrl->regmap_nfi, REG_SPI_NFI_SECCUS_SIZE, &val);
-	if (err)
-		return err;
-
-	sec_size = FIELD_GET(SPI_NFI_CUS_SEC_SIZE, val);
-
-	/* init default value */
-	as_ctrl->nfi_cfg.sec_size = sec_size;
-	as_ctrl->nfi_cfg.sec_num = sec_num;
-	as_ctrl->nfi_cfg.page_size = round_down(sec_size * sec_num, 1024);
-	as_ctrl->nfi_cfg.spare_size = 16;
-
-	err = airoha_snand_nfi_init(as_ctrl);
-	if (err)
-		return err;
-
-	return airoha_snand_nfi_config(as_ctrl);
-}
-
 static const struct regmap_config spi_ctrl_regmap_config = {
 	.name		= "ctrl",
 	.reg_bits	= 32,
@@ -1104,7 +1062,9 @@ static int airoha_snand_probe(struct platform_device *pdev)
 	struct airoha_snand_ctrl *as_ctrl;
 	struct device *dev = &pdev->dev;
 	struct spi_controller *ctrl;
+	bool dma_enable = true;
 	void __iomem *base;
+	u32 sfc_strap;
 	int err;
 
 	ctrl = devm_spi_alloc_host(dev, sizeof(*as_ctrl));
@@ -1139,18 +1099,34 @@ static int airoha_snand_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(as_ctrl->spi_clk),
 				     "unable to get spi clk\n");
 
+	if (device_is_compatible(dev, "airoha,en7523-snand")) {
+		err = regmap_read(as_ctrl->regmap_ctrl,
+				  REG_SPI_CTRL_SFC_STRAP, &sfc_strap);
+		if (err)
+			return err;
+
+		if (!(sfc_strap & 0x04)) {
+			dma_enable = false;
+			dev_warn(dev, "Detected booting in RESERVED mode (UART_TXD was short to GND).\n");
+			dev_warn(dev, "This mode is known for incorrect DMA reading of some flashes.\n");
+			dev_warn(dev, "Much slower PIO mode will be used to prevent flash data damage.\n");
+			dev_warn(dev, "Unplug UART cable and power cycle board to get full performance.\n");
+		}
+	}
+
 	err = dma_set_mask(as_ctrl->dev, DMA_BIT_MASK(32));
 	if (err)
 		return err;
 
 	ctrl->num_chipselect = 2;
-	ctrl->mem_ops = &airoha_snand_mem_ops;
+	ctrl->mem_ops = dma_enable ? &airoha_snand_mem_ops
+				   : &airoha_snand_nodma_mem_ops;
 	ctrl->bits_per_word_mask = SPI_BPW_MASK(8);
 	ctrl->mode_bits = SPI_RX_DUAL;
 	ctrl->setup = airoha_snand_setup;
 	device_set_node(&ctrl->dev, dev_fwnode(dev));
 
-	err = airoha_snand_nfi_setup(as_ctrl);
+	err = airoha_snand_nfi_init(as_ctrl);
 	if (err)
 		return err;
 
diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c
index 62a1114..db3e096 100644
--- a/drivers/spi/spi-aspeed-smc.c
+++ b/drivers/spi/spi-aspeed-smc.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
@@ -67,6 +68,7 @@ struct aspeed_spi_chip {
 	u32			 ahb_window_size;
 	u32			 ctl_val[ASPEED_SPI_MAX];
 	u32			 clk_freq;
+	bool			 force_user_mode;
 };
 
 struct aspeed_spi_data {
@@ -78,10 +80,14 @@ struct aspeed_spi_data {
 	u32	timing;
 	u32	hclk_mask;
 	u32	hdiv_max;
-
-	u32 (*segment_start)(struct aspeed_spi *aspi, u32 reg);
-	u32 (*segment_end)(struct aspeed_spi *aspi, u32 reg);
-	u32 (*segment_reg)(struct aspeed_spi *aspi, u32 start, u32 end);
+	u32	min_window_size;
+
+	phys_addr_t (*segment_start)(struct aspeed_spi *aspi, u32 reg);
+	phys_addr_t (*segment_end)(struct aspeed_spi *aspi, u32 reg);
+	u32 (*segment_reg)(struct aspeed_spi *aspi, phys_addr_t start,
+			   phys_addr_t end);
+	int (*adjust_window)(struct aspeed_spi *aspi);
+	u32 (*get_clk_div)(struct aspeed_spi_chip *chip, u32 hz);
 	int (*calibrate)(struct aspeed_spi_chip *chip, u32 hdiv,
 			 const u8 *golden_buf, u8 *test_buf);
 };
@@ -92,9 +98,9 @@ struct aspeed_spi {
 	const struct aspeed_spi_data	*data;
 
 	void __iomem		*regs;
-	void __iomem		*ahb_base;
-	u32			 ahb_base_phy;
+	phys_addr_t		 ahb_base_phy;
 	u32			 ahb_window_size;
+	u32			 num_cs;
 	struct device		*dev;
 
 	struct clk		*clk;
@@ -258,11 +264,15 @@ static ssize_t aspeed_spi_write_user(struct aspeed_spi_chip *chip,
 				     const struct spi_mem_op *op)
 {
 	int ret;
+	int io_mode = aspeed_spi_get_io_mode(op);
 
 	aspeed_spi_start_user(chip);
 	ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, op->addr.val, op->cmd.opcode);
 	if (ret < 0)
 		goto stop_user;
+
+	aspeed_spi_set_io_mode(chip, io_mode);
+
 	aspeed_spi_write_to_ahb(chip->ahb_base, op->data.buf.out, op->data.nbytes);
 stop_user:
 	aspeed_spi_stop_user(chip);
@@ -376,89 +386,270 @@ static const char *aspeed_spi_get_name(struct spi_mem *mem)
 			      spi_get_chipselect(mem->spi, 0));
 }
 
-struct aspeed_spi_window {
+static int aspeed_spi_set_window(struct aspeed_spi *aspi)
+{
+	struct device *dev = aspi->dev;
+	off_t offset = 0;
+	phys_addr_t start;
+	phys_addr_t end;
+	void __iomem *seg_reg_base = aspi->regs + CE0_SEGMENT_ADDR_REG;
+	void __iomem *seg_reg;
+	u32 seg_val_backup;
+	u32 seg_val;
 	u32 cs;
-	u32 offset;
-	u32 size;
-};
+	size_t window_size;
+
+	for (cs = 0; cs < aspi->data->max_cs; cs++) {
+		if (aspi->chips[cs].ahb_base) {
+			devm_iounmap(dev, aspi->chips[cs].ahb_base);
+			aspi->chips[cs].ahb_base = NULL;
+		}
+	}
+
+	for (cs = 0; cs < aspi->data->max_cs; cs++) {
+		seg_reg = seg_reg_base + cs * 4;
+		seg_val_backup = readl(seg_reg);
+
+		start = aspi->ahb_base_phy + offset;
+		window_size = aspi->chips[cs].ahb_window_size;
+		end = start + window_size;
+
+		seg_val = aspi->data->segment_reg(aspi, start, end);
+		writel(seg_val, seg_reg);
+
+		/*
+		 * Restore initial value if something goes wrong or the segment
+		 * register is written protected.
+		 */
+		if (seg_val != readl(seg_reg)) {
+			dev_warn(dev, "CE%d expected window [ 0x%.9llx - 0x%.9llx ] %zdMB\n",
+				 cs, (u64)start, (u64)end - 1, window_size >> 20);
+			writel(seg_val_backup, seg_reg);
+			window_size = aspi->data->segment_end(aspi, seg_val_backup) -
+				      aspi->data->segment_start(aspi, seg_val_backup);
+			aspi->chips[cs].ahb_window_size = window_size;
+			end = start + window_size;
+		}
+
+		if (window_size != 0)
+			dev_dbg(dev, "CE%d window [ 0x%.9llx - 0x%.9llx ] %zdMB\n",
+				cs, (u64)start, (u64)end - 1,  window_size >> 20);
+		else
+			dev_dbg(dev, "CE%d window closed\n", cs);
+
+		offset += window_size;
+		if (offset > aspi->ahb_window_size) {
+			dev_err(dev, "CE%d offset value 0x%llx is too large.\n",
+				cs, (u64)offset);
+			return -ENOSPC;
+		}
+
+		/*
+		 * No need to map the address deocding range when
+		 * - window size is 0.
+		 * - the CS is unused.
+		 */
+		if (window_size == 0 || cs >= aspi->num_cs)
+			continue;
+
+		aspi->chips[cs].ahb_base =
+			devm_ioremap(aspi->dev, start, window_size);
+		if (!aspi->chips[cs].ahb_base) {
+			dev_err(aspi->dev,
+				"Fail to remap window [0x%.9llx - 0x%.9llx]\n",
+				(u64)start, (u64)end - 1);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct aspeed_spi_data ast2500_spi_data;
+static const struct aspeed_spi_data ast2600_spi_data;
+static const struct aspeed_spi_data ast2600_fmc_data;
 
-static void aspeed_spi_get_windows(struct aspeed_spi *aspi,
-				   struct aspeed_spi_window windows[ASPEED_SPI_MAX_NUM_CS])
+static int aspeed_spi_chip_set_default_window(struct aspeed_spi *aspi)
 {
-	const struct aspeed_spi_data *data = aspi->data;
-	u32 reg_val;
 	u32 cs;
 
-	for (cs = 0; cs < aspi->data->max_cs; cs++) {
-		reg_val = readl(aspi->regs + CE0_SEGMENT_ADDR_REG + cs * 4);
-		windows[cs].cs = cs;
-		windows[cs].size = data->segment_end(aspi, reg_val) -
-			data->segment_start(aspi, reg_val);
-		windows[cs].offset = data->segment_start(aspi, reg_val) - aspi->ahb_base_phy;
-		dev_vdbg(aspi->dev, "CE%d offset=0x%.8x size=0x%x\n", cs,
-			 windows[cs].offset, windows[cs].size);
+	/* No segment registers for the AST2400 SPI controller */
+	if (aspi->data == &ast2400_spi_data) {
+		aspi->chips[0].ahb_base = devm_ioremap(aspi->dev,
+						       aspi->ahb_base_phy,
+						       aspi->ahb_window_size);
+		aspi->chips[0].ahb_window_size = aspi->ahb_window_size;
+		return 0;
 	}
+
+	/* Assign the minimum window size to each CS */
+	for (cs = 0; cs < aspi->num_cs; cs++) {
+		aspi->chips[cs].ahb_window_size = aspi->data->min_window_size;
+		dev_dbg(aspi->dev, "CE%d default window [ 0x%.9llx - 0x%.9llx ]",
+			cs, (u64)(aspi->ahb_base_phy + aspi->data->min_window_size * cs),
+			(u64)(aspi->ahb_base_phy + aspi->data->min_window_size * cs - 1));
+	}
+
+	/* Close unused CS */
+	for (cs = aspi->num_cs; cs < aspi->data->max_cs; cs++)
+		aspi->chips[cs].ahb_window_size = 0;
+
+	if (aspi->data->adjust_window)
+		aspi->data->adjust_window(aspi);
+
+	return aspeed_spi_set_window(aspi);
 }
 
 /*
- * On the AST2600, some CE windows are closed by default at reset but
- * U-Boot should open all.
+ * As the flash size grows up, we need to trim some decoding
+ * size if needed for the sake of conforming the maximum
+ * decoding size. We trim the decoding size from the rear CS
+ * to avoid affecting the default boot up sequence, usually,
+ * from CS0. Notice, if a CS decoding size is trimmed,
+ * command mode may not work perfectly on that CS, but it only
+ * affect performance and the debug function.
  */
-static int aspeed_spi_chip_set_default_window(struct aspeed_spi_chip *chip)
+static int aspeed_spi_trim_window_size(struct aspeed_spi *aspi)
 {
-	struct aspeed_spi *aspi = chip->aspi;
-	struct aspeed_spi_window windows[ASPEED_SPI_MAX_NUM_CS] = { 0 };
-	struct aspeed_spi_window *win = &windows[chip->cs];
+	struct aspeed_spi_chip *chips = aspi->chips;
+	size_t total_sz;
+	int cs = aspi->data->max_cs - 1;
+	u32 i;
+	bool trimmed = false;
+
+	do {
+		total_sz = 0;
+		for (i = 0; i < aspi->data->max_cs; i++)
+			total_sz += chips[i].ahb_window_size;
+
+		if (cs < 0)
+			return -ENOMEM;
+
+		if (chips[cs].ahb_window_size <= aspi->data->min_window_size) {
+			cs--;
+			continue;
+		}
 
-	/* No segment registers for the AST2400 SPI controller */
-	if (aspi->data == &ast2400_spi_data) {
-		win->offset = 0;
-		win->size = aspi->ahb_window_size;
-	} else {
-		aspeed_spi_get_windows(aspi, windows);
+		if (total_sz > aspi->ahb_window_size) {
+			chips[cs].ahb_window_size -=
+				aspi->data->min_window_size;
+			total_sz -= aspi->data->min_window_size;
+			/*
+			 * If the ahb window size is ever trimmed, only user
+			 * mode can be adopted to access the whole flash.
+			 */
+			chips[cs].force_user_mode = true;
+			trimmed = true;
+		}
+	} while (total_sz > aspi->ahb_window_size);
+
+	if (trimmed) {
+		dev_warn(aspi->dev, "Window size after trimming:\n");
+		for (cs = 0; cs < aspi->data->max_cs; cs++) {
+			dev_warn(aspi->dev, "CE%d: 0x%08x\n",
+				 cs, chips[cs].ahb_window_size);
+		}
 	}
 
-	chip->ahb_base = aspi->ahb_base + win->offset;
-	chip->ahb_window_size = win->size;
+	return 0;
+}
+
+static int aspeed_adjust_window_ast2400(struct aspeed_spi *aspi)
+{
+	int ret;
+	int cs;
+	struct aspeed_spi_chip *chips = aspi->chips;
+
+	/* Close unused CS. */
+	for (cs = aspi->num_cs; cs < aspi->data->max_cs; cs++)
+		chips[cs].ahb_window_size = 0;
 
-	dev_dbg(aspi->dev, "CE%d default window [ 0x%.8x - 0x%.8x ] %dMB",
-		chip->cs, aspi->ahb_base_phy + win->offset,
-		aspi->ahb_base_phy + win->offset + win->size - 1,
-		win->size >> 20);
+	ret = aspeed_spi_trim_window_size(aspi);
+	if (ret != 0)
+		return ret;
 
-	return chip->ahb_window_size ? 0 : -1;
+	return 0;
 }
 
-static int aspeed_spi_set_window(struct aspeed_spi *aspi,
-				 const struct aspeed_spi_window *win)
+/*
+ * For AST2500, the minimum address decoding size for each CS
+ * is 8MB. This address decoding size is mandatory for each
+ * CS no matter whether it will be used. This is a HW limitation.
+ */
+static int aspeed_adjust_window_ast2500(struct aspeed_spi *aspi)
 {
-	u32 start = aspi->ahb_base_phy + win->offset;
-	u32 end = start + win->size;
-	void __iomem *seg_reg = aspi->regs + CE0_SEGMENT_ADDR_REG + win->cs * 4;
-	u32 seg_val_backup = readl(seg_reg);
-	u32 seg_val = aspi->data->segment_reg(aspi, start, end);
+	int ret;
+	int cs, i;
+	u32 cum_size, rem_size;
+	struct aspeed_spi_chip *chips = aspi->chips;
+
+	/* Assign min_window_sz to unused CS. */
+	for (cs = aspi->num_cs; cs < aspi->data->max_cs; cs++) {
+		if (chips[cs].ahb_window_size < aspi->data->min_window_size)
+			chips[cs].ahb_window_size =
+				aspi->data->min_window_size;
+	}
 
-	if (seg_val == seg_val_backup)
-		return 0;
+	/*
+	 * If command mode or normal mode is used by dirmap read, the start
+	 * address of a window should be multiple of its related flash size.
+	 * Namely, the total windows size from flash 0 to flash N should
+	 * be multiple of the size of flash (N + 1).
+	 */
+	for (cs = aspi->num_cs - 1; cs >= 0; cs--) {
+		cum_size = 0;
+		for (i = 0; i < cs; i++)
+			cum_size += chips[i].ahb_window_size;
+
+		rem_size = cum_size % chips[cs].ahb_window_size;
+		if (chips[cs].ahb_window_size != 0 && rem_size != 0)
+			chips[0].ahb_window_size +=
+				chips[cs].ahb_window_size - rem_size;
+	}
+
+	ret = aspeed_spi_trim_window_size(aspi);
+	if (ret != 0)
+		return ret;
+
+	/* The total window size of AST2500 SPI1 CS0 and CS1 must be 128MB */
+	if (aspi->data == &ast2500_spi_data)
+		chips[1].ahb_window_size =
+			0x08000000 - chips[0].ahb_window_size;
+
+	return 0;
+}
+
+static int aspeed_adjust_window_ast2600(struct aspeed_spi *aspi)
+{
+	int ret;
+	int cs, i;
+	u32 cum_size, rem_size;
+	struct aspeed_spi_chip *chips = aspi->chips;
 
-	writel(seg_val, seg_reg);
+	/* Close unused CS. */
+	for (cs = aspi->num_cs; cs < aspi->data->max_cs; cs++)
+		chips[cs].ahb_window_size = 0;
 
 	/*
-	 * Restore initial value if something goes wrong else we could
-	 * loose access to the chip.
+	 * If command mode or normal mode is used by dirmap read, the start
+	 * address of a window should be multiple of its related flash size.
+	 * Namely, the total windows size from flash 0 to flash N should
+	 * be multiple of the size of flash (N + 1).
 	 */
-	if (seg_val != readl(seg_reg)) {
-		dev_err(aspi->dev, "CE%d invalid window [ 0x%.8x - 0x%.8x ] %dMB",
-			win->cs, start, end - 1, win->size >> 20);
-		writel(seg_val_backup, seg_reg);
-		return -EIO;
+	for (cs = aspi->num_cs - 1; cs >= 0; cs--) {
+		cum_size = 0;
+		for (i = 0; i < cs; i++)
+			cum_size += chips[i].ahb_window_size;
+
+		rem_size = cum_size % chips[cs].ahb_window_size;
+		if (chips[cs].ahb_window_size != 0 && rem_size != 0)
+			chips[0].ahb_window_size +=
+				chips[cs].ahb_window_size - rem_size;
 	}
 
-	if (win->size)
-		dev_dbg(aspi->dev, "CE%d new window [ 0x%.8x - 0x%.8x ] %dMB",
-			win->cs, start, end - 1,  win->size >> 20);
-	else
-		dev_dbg(aspi->dev, "CE%d window closed", win->cs);
+	ret = aspeed_spi_trim_window_size(aspi);
+	if (ret != 0)
+		return ret;
 
 	return 0;
 }
@@ -469,78 +660,27 @@ static int aspeed_spi_set_window(struct aspeed_spi *aspi,
  * - ioremap each window, not strictly necessary since the overall window
  *   is correct.
  */
-static const struct aspeed_spi_data ast2500_spi_data;
-static const struct aspeed_spi_data ast2600_spi_data;
-static const struct aspeed_spi_data ast2600_fmc_data;
-
 static int aspeed_spi_chip_adjust_window(struct aspeed_spi_chip *chip,
 					 u32 local_offset, u32 size)
 {
 	struct aspeed_spi *aspi = chip->aspi;
-	struct aspeed_spi_window windows[ASPEED_SPI_MAX_NUM_CS] = { 0 };
-	struct aspeed_spi_window *win = &windows[chip->cs];
 	int ret;
 
 	/* No segment registers for the AST2400 SPI controller */
 	if (aspi->data == &ast2400_spi_data)
 		return 0;
 
-	/*
-	 * Due to an HW issue on the AST2500 SPI controller, the CE0
-	 * window size should be smaller than the maximum 128MB.
-	 */
-	if (aspi->data == &ast2500_spi_data && chip->cs == 0 && size == SZ_128M) {
-		size = 120 << 20;
-		dev_info(aspi->dev, "CE%d window resized to %dMB (AST2500 HW quirk)",
-			 chip->cs, size >> 20);
-	}
-
-	/*
-	 * The decoding size of AST2600 SPI controller should set at
-	 * least 2MB.
-	 */
-	if ((aspi->data == &ast2600_spi_data || aspi->data == &ast2600_fmc_data) &&
-	    size < SZ_2M) {
-		size = SZ_2M;
-		dev_info(aspi->dev, "CE%d window resized to %dMB (AST2600 Decoding)",
-			 chip->cs, size >> 20);
-	}
-
-	aspeed_spi_get_windows(aspi, windows);
-
 	/* Adjust this chip window */
-	win->offset += local_offset;
-	win->size = size;
+	aspi->chips[chip->cs].ahb_window_size = size;
 
-	if (win->offset + win->size > aspi->ahb_window_size) {
-		win->size = aspi->ahb_window_size - win->offset;
-		dev_warn(aspi->dev, "CE%d window resized to %dMB", chip->cs, win->size >> 20);
-	}
+	/* Adjust the overall windows size regarding each platform */
+	if (aspi->data->adjust_window)
+		aspi->data->adjust_window(aspi);
 
-	ret = aspeed_spi_set_window(aspi, win);
+	ret = aspeed_spi_set_window(aspi);
 	if (ret)
 		return ret;
 
-	/* Update chip mapping info */
-	chip->ahb_base = aspi->ahb_base + win->offset;
-	chip->ahb_window_size = win->size;
-
-	/*
-	 * Also adjust next chip window to make sure that it does not
-	 * overlap with the current window.
-	 */
-	if (chip->cs < aspi->data->max_cs - 1) {
-		struct aspeed_spi_window *next = &windows[chip->cs + 1];
-
-		/* Change offset and size to keep the same end address */
-		if ((next->offset + next->size) > (win->offset + win->size))
-			next->size = (next->offset + next->size) - (win->offset + win->size);
-		else
-			next->size = 0;
-		next->offset = win->offset + win->size;
-
-		aspeed_spi_set_window(aspi, next);
-	}
 	return 0;
 }
 
@@ -619,7 +759,7 @@ static ssize_t aspeed_spi_dirmap_read(struct spi_mem_dirmap_desc *desc,
 	struct aspeed_spi_chip *chip = &aspi->chips[spi_get_chipselect(desc->mem->spi, 0)];
 
 	/* Switch to USER command mode if mapping window is too small */
-	if (chip->ahb_window_size < offset + len) {
+	if (chip->ahb_window_size < offset + len || chip->force_user_mode) {
 		int ret;
 
 		ret = aspeed_spi_read_user(chip, &desc->info.op_tmpl, offset, len, buf);
@@ -677,11 +817,6 @@ static int aspeed_spi_setup(struct spi_device *spi)
 	if (data->hastype)
 		aspeed_spi_chip_set_type(aspi, cs, CONFIG_TYPE_SPI);
 
-	if (aspeed_spi_chip_set_default_window(chip) < 0) {
-		dev_warn(aspi->dev, "CE%d window invalid", cs);
-		return -EINVAL;
-	}
-
 	aspeed_spi_chip_enable(aspi, cs, true);
 
 	chip->ctl_val[ASPEED_SPI_BASE] = CTRL_CE_STOP_ACTIVE | CTRL_IO_MODE_USER;
@@ -734,10 +869,10 @@ static int aspeed_spi_probe(struct platform_device *pdev)
 	if (IS_ERR(aspi->regs))
 		return PTR_ERR(aspi->regs);
 
-	aspi->ahb_base = devm_platform_get_and_ioremap_resource(pdev, 1, &res);
-	if (IS_ERR(aspi->ahb_base)) {
-		dev_err(dev, "missing AHB mapping window\n");
-		return PTR_ERR(aspi->ahb_base);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res) {
+		dev_err(dev, "missing AHB memory\n");
+		return -EINVAL;
 	}
 
 	aspi->ahb_window_size = resource_size(res);
@@ -762,9 +897,17 @@ static int aspeed_spi_probe(struct platform_device *pdev)
 	ctlr->mem_ops = &aspeed_spi_mem_ops;
 	ctlr->setup = aspeed_spi_setup;
 	ctlr->cleanup = aspeed_spi_cleanup;
-	ctlr->num_chipselect = data->max_cs;
+	ctlr->num_chipselect = of_get_available_child_count(dev->of_node);
 	ctlr->dev.of_node = dev->of_node;
 
+	aspi->num_cs = ctlr->num_chipselect;
+
+	ret = aspeed_spi_chip_set_default_window(aspi);
+	if (ret) {
+		dev_err(&pdev->dev, "fail to set default window\n");
+		return ret;
+	}
+
 	ret = devm_spi_register_controller(dev, ctlr);
 	if (ret)
 		dev_err(&pdev->dev, "spi_register_controller failed\n");
@@ -788,17 +931,18 @@ static void aspeed_spi_remove(struct platform_device *pdev)
  * The address range is encoded with absolute addresses in the overall
  * mapping window.
  */
-static u32 aspeed_spi_segment_start(struct aspeed_spi *aspi, u32 reg)
+static phys_addr_t aspeed_spi_segment_start(struct aspeed_spi *aspi, u32 reg)
 {
 	return ((reg >> 16) & 0xFF) << 23;
 }
 
-static u32 aspeed_spi_segment_end(struct aspeed_spi *aspi, u32 reg)
+static phys_addr_t aspeed_spi_segment_end(struct aspeed_spi *aspi, u32 reg)
 {
 	return ((reg >> 24) & 0xFF) << 23;
 }
 
-static u32 aspeed_spi_segment_reg(struct aspeed_spi *aspi, u32 start, u32 end)
+static u32 aspeed_spi_segment_reg(struct aspeed_spi *aspi,
+				  phys_addr_t start, phys_addr_t end)
 {
 	return (((start >> 23) & 0xFF) << 16) | (((end >> 23) & 0xFF) << 24);
 }
@@ -810,16 +954,16 @@ static u32 aspeed_spi_segment_reg(struct aspeed_spi *aspi, u32 start, u32 end)
 
 #define AST2600_SEG_ADDR_MASK 0x0ff00000
 
-static u32 aspeed_spi_segment_ast2600_start(struct aspeed_spi *aspi,
-					    u32 reg)
+static phys_addr_t aspeed_spi_segment_ast2600_start(struct aspeed_spi *aspi,
+						    u32 reg)
 {
 	u32 start_offset = (reg << 16) & AST2600_SEG_ADDR_MASK;
 
 	return aspi->ahb_base_phy + start_offset;
 }
 
-static u32 aspeed_spi_segment_ast2600_end(struct aspeed_spi *aspi,
-					  u32 reg)
+static phys_addr_t aspeed_spi_segment_ast2600_end(struct aspeed_spi *aspi,
+						  u32 reg)
 {
 	u32 end_offset = reg & AST2600_SEG_ADDR_MASK;
 
@@ -831,7 +975,7 @@ static u32 aspeed_spi_segment_ast2600_end(struct aspeed_spi *aspi,
 }
 
 static u32 aspeed_spi_segment_ast2600_reg(struct aspeed_spi *aspi,
-					  u32 start, u32 end)
+					  phys_addr_t start, phys_addr_t end)
 {
 	/* disable zero size segments */
 	if (start == end)
@@ -841,6 +985,41 @@ static u32 aspeed_spi_segment_ast2600_reg(struct aspeed_spi *aspi,
 		((end - 1) & AST2600_SEG_ADDR_MASK);
 }
 
+/* The Segment Registers of the AST2700 use a 64KB unit. */
+#define AST2700_SEG_ADDR_MASK 0x7fff0000
+
+static phys_addr_t aspeed_spi_segment_ast2700_start(struct aspeed_spi *aspi,
+						    u32 reg)
+{
+	u64 start_offset = (reg << 16) & AST2700_SEG_ADDR_MASK;
+
+	if (!start_offset)
+		return aspi->ahb_base_phy;
+
+	return aspi->ahb_base_phy + start_offset;
+}
+
+static phys_addr_t aspeed_spi_segment_ast2700_end(struct aspeed_spi *aspi,
+						  u32 reg)
+{
+	u64 end_offset = reg & AST2700_SEG_ADDR_MASK;
+
+	if (!end_offset)
+		return aspi->ahb_base_phy;
+
+	return aspi->ahb_base_phy + end_offset;
+}
+
+static u32 aspeed_spi_segment_ast2700_reg(struct aspeed_spi *aspi,
+					  phys_addr_t start, phys_addr_t end)
+{
+	if (start == end)
+		return 0;
+
+	return (u32)(((start & AST2700_SEG_ADDR_MASK) >> 16) |
+		     (end & AST2700_SEG_ADDR_MASK));
+}
+
 /*
  * Read timing compensation sequences
  */
@@ -942,26 +1121,149 @@ static bool aspeed_spi_check_calib_data(const u8 *test_buf, u32 size)
 }
 
 static const u32 aspeed_spi_hclk_divs[] = {
-	0xf, /* HCLK */
-	0x7, /* HCLK/2 */
-	0xe, /* HCLK/3 */
-	0x6, /* HCLK/4 */
-	0xd, /* HCLK/5 */
+	/* HCLK, HCLK/2, HCLK/3, HCLK/4, HCLK/5, ..., HCLK/16 */
+	0xf, 0x7, 0xe, 0x6, 0xd,
+	0x5, 0xc, 0x4, 0xb, 0x3,
+	0xa, 0x2, 0x9, 0x1, 0x8,
+	0x0
 };
 
 #define ASPEED_SPI_HCLK_DIV(i) \
 	(aspeed_spi_hclk_divs[(i) - 1] << CTRL_FREQ_SEL_SHIFT)
 
+/* Transfer maximum clock frequency to register setting */
+static u32 aspeed_get_clk_div_ast2400(struct aspeed_spi_chip *chip,
+				      u32 max_hz)
+{
+	struct device *dev = chip->aspi->dev;
+	u32 hclk_clk = chip->aspi->clk_freq;
+	u32 div_ctl = 0;
+	u32 i;
+	bool found = false;
+
+	/* FMC/SPIR10[11:8] */
+	for (i = 1; i <= ARRAY_SIZE(aspeed_spi_hclk_divs); i++) {
+		if (hclk_clk / i <= max_hz) {
+			found = true;
+			break;
+		}
+	}
+
+	if (found) {
+		div_ctl = ASPEED_SPI_HCLK_DIV(i);
+		chip->clk_freq = hclk_clk / i;
+	}
+
+	dev_dbg(dev, "found: %s, hclk: %d, max_clk: %d\n",
+		found ? "yes" : "no", hclk_clk, max_hz);
+
+	if (found) {
+		dev_dbg(dev, "h_div: 0x%08x, speed: %d\n",
+			div_ctl, chip->clk_freq);
+	}
+
+	return div_ctl;
+}
+
+static u32 aspeed_get_clk_div_ast2500(struct aspeed_spi_chip *chip,
+				      u32 max_hz)
+{
+	struct device *dev = chip->aspi->dev;
+	u32 hclk_clk = chip->aspi->clk_freq;
+	u32 div_ctl = 0;
+	u32 i;
+	bool found = false;
+
+	/* FMC/SPIR10[11:8] */
+	for (i = 1; i <= ARRAY_SIZE(aspeed_spi_hclk_divs); i++) {
+		if (hclk_clk / i <= max_hz) {
+			found = true;
+			chip->clk_freq = hclk_clk / i;
+			break;
+		}
+	}
+
+	if (found) {
+		div_ctl = ASPEED_SPI_HCLK_DIV(i);
+		goto end;
+	}
+
+	for (i = 1; i <= ARRAY_SIZE(aspeed_spi_hclk_divs); i++) {
+		if (hclk_clk / (i * 4) <= max_hz) {
+			found = true;
+			chip->clk_freq = hclk_clk / (i * 4);
+			break;
+		}
+	}
+
+	if (found)
+		div_ctl = BIT(13) | ASPEED_SPI_HCLK_DIV(i);
+
+end:
+	dev_dbg(dev, "found: %s, hclk: %d, max_clk: %d\n",
+		found ? "yes" : "no", hclk_clk, max_hz);
+
+	if (found) {
+		dev_dbg(dev, "h_div: 0x%08x, speed: %d\n",
+			div_ctl, chip->clk_freq);
+	}
+
+	return div_ctl;
+}
+
+static u32 aspeed_get_clk_div_ast2600(struct aspeed_spi_chip *chip,
+				      u32 max_hz)
+{
+	struct device *dev = chip->aspi->dev;
+	u32 hclk_clk = chip->aspi->clk_freq;
+	u32 div_ctl = 0;
+	u32 i, j;
+	bool found = false;
+
+	/* FMC/SPIR10[27:24] */
+	for (j = 0; j < 16; j++) {
+		/* FMC/SPIR10[11:8] */
+		for (i = 1; i <= ARRAY_SIZE(aspeed_spi_hclk_divs); i++) {
+			if (j == 0 && i == 1)
+				continue;
+
+			if (hclk_clk / (j * 16 + i) <= max_hz) {
+				found = true;
+				break;
+			}
+		}
+
+		if (found) {
+			div_ctl = ((j << 24) | ASPEED_SPI_HCLK_DIV(i));
+			chip->clk_freq = hclk_clk / (j * 16 + i);
+			break;
+		}
+	}
+
+	dev_dbg(dev, "found: %s, hclk: %d, max_clk: %d\n",
+		found ? "yes" : "no", hclk_clk, max_hz);
+
+	if (found) {
+		dev_dbg(dev, "h_div: 0x%08x, speed: %d\n",
+			div_ctl, chip->clk_freq);
+	}
+
+	return div_ctl;
+}
+
 static int aspeed_spi_do_calibration(struct aspeed_spi_chip *chip)
 {
 	struct aspeed_spi *aspi = chip->aspi;
 	const struct aspeed_spi_data *data = aspi->data;
 	u32 ahb_freq = aspi->clk_freq;
 	u32 max_freq = chip->clk_freq;
+	bool exec_calib = false;
+	u32 best_freq = 0;
 	u32 ctl_val;
 	u8 *golden_buf = NULL;
 	u8 *test_buf = NULL;
-	int i, rc, best_div = -1;
+	int i, rc;
+	u32 div_ctl;
 
 	dev_dbg(aspi->dev, "calculate timing compensation - AHB freq: %d MHz",
 		ahb_freq / 1000000);
@@ -982,7 +1284,7 @@ static int aspeed_spi_do_calibration(struct aspeed_spi_chip *chip)
 	memcpy_fromio(golden_buf, chip->ahb_base, CALIBRATE_BUF_SIZE);
 	if (!aspeed_spi_check_calib_data(golden_buf, CALIBRATE_BUF_SIZE)) {
 		dev_info(aspi->dev, "Calibration area too uniform, using low speed");
-		goto no_calib;
+		goto end_calib;
 	}
 
 #if defined(VERBOSE_DEBUG)
@@ -991,7 +1293,7 @@ static int aspeed_spi_do_calibration(struct aspeed_spi_chip *chip)
 #endif
 
 	/* Now we iterate the HCLK dividers until we find our breaking point */
-	for (i = ARRAY_SIZE(aspeed_spi_hclk_divs); i > data->hdiv_max - 1; i--) {
+	for (i = 5; i > data->hdiv_max - 1; i--) {
 		u32 tv, freq;
 
 		freq = ahb_freq / i;
@@ -1004,22 +1306,33 @@ static int aspeed_spi_do_calibration(struct aspeed_spi_chip *chip)
 		dev_dbg(aspi->dev, "Trying HCLK/%d [%08x] ...", i, tv);
 		rc = data->calibrate(chip, i, golden_buf, test_buf);
 		if (rc == 0)
-			best_div = i;
+			best_freq = freq;
+
+		exec_calib = true;
 	}
 
-	/* Nothing found ? */
-	if (best_div < 0) {
-		dev_warn(aspi->dev, "No good frequency, using dumb slow");
+end_calib:
+	if (!exec_calib) {
+		/* calibration process is not executed */
+		dev_warn(aspi->dev, "Force to dts configuration %dkHz.\n",
+			 max_freq / 1000);
+		div_ctl = data->get_clk_div(chip, max_freq);
+	} else if (best_freq == 0) {
+		/* calibration process is executed, but no good frequency */
+		dev_warn(aspi->dev, "No good frequency, using dumb slow\n");
+		div_ctl = 0;
 	} else {
-		dev_dbg(aspi->dev, "Found good read timings at HCLK/%d", best_div);
+		dev_dbg(aspi->dev, "Found good read timings at %dMHz.\n",
+			best_freq / 1000000);
+		div_ctl = data->get_clk_div(chip, best_freq);
+	}
 
-		/* Record the freq */
-		for (i = 0; i < ASPEED_SPI_MAX; i++)
-			chip->ctl_val[i] = (chip->ctl_val[i] & data->hclk_mask) |
-				ASPEED_SPI_HCLK_DIV(best_div);
+	/* Record the freq */
+	for (i = 0; i < ASPEED_SPI_MAX; i++) {
+		chip->ctl_val[i] = (chip->ctl_val[i] & data->hclk_mask) |
+				   div_ctl;
 	}
 
-no_calib:
 	writel(chip->ctl_val[ASPEED_SPI_READ], chip->ctl);
 	kfree(test_buf);
 	return 0;
@@ -1027,21 +1340,57 @@ no_calib:
 
 #define TIMING_DELAY_DI		BIT(3)
 #define TIMING_DELAY_HCYCLE_MAX	5
+#define TIMING_DELAY_INPUT_MAX	16
 #define TIMING_REG_AST2600(chip)				\
 	((chip)->aspi->regs + (chip)->aspi->data->timing +	\
 	 (chip)->cs * 4)
 
+/*
+ * This function returns the center point of the longest
+ * continuous "pass" interval within the buffer. The interval
+ * must contains the highest number of consecutive "pass"
+ * results and not span across multiple rows.
+ */
+static u32 aspeed_spi_ast2600_optimized_timing(u32 rows, u32 cols,
+					       u8 buf[rows][cols])
+{
+	int r = 0, c = 0;
+	int max = 0;
+	int i, j;
+
+	for (i = 0; i < rows; i++) {
+		for (j = 0; j < cols;) {
+			int k = j;
+
+			while (k < cols && buf[i][k])
+				k++;
+
+			if (k - j > max) {
+				max = k - j;
+				r = i;
+				c = j + (k - j) / 2;
+			}
+
+			j = k + 1;
+		}
+	}
+
+	return max > 4 ? r * cols + c : 0;
+}
+
 static int aspeed_spi_ast2600_calibrate(struct aspeed_spi_chip *chip, u32 hdiv,
 					const u8 *golden_buf, u8 *test_buf)
 {
 	struct aspeed_spi *aspi = chip->aspi;
 	int hcycle;
+	int delay_ns;
 	u32 shift = (hdiv - 2) << 3;
-	u32 mask = ~(0xfu << shift);
+	u32 mask = ~(0xffu << shift);
 	u32 fread_timing_val = 0;
+	u8 calib_res[6][17] = {0};
+	u32 calib_point;
 
 	for (hcycle = 0; hcycle <= TIMING_DELAY_HCYCLE_MAX; hcycle++) {
-		int delay_ns;
 		bool pass = false;
 
 		fread_timing_val &= mask;
@@ -1054,14 +1403,14 @@ static int aspeed_spi_ast2600_calibrate(struct aspeed_spi_chip *chip, u32 hdiv,
 			"  * [%08x] %d HCLK delay, DI delay none : %s",
 			fread_timing_val, hcycle, pass ? "PASS" : "FAIL");
 		if (pass)
-			return 0;
+			calib_res[hcycle][0] = 1;
 
 		/* Add DI input delays  */
 		fread_timing_val &= mask;
 		fread_timing_val |= (TIMING_DELAY_DI | hcycle) << shift;
 
-		for (delay_ns = 0; delay_ns < 0x10; delay_ns++) {
-			fread_timing_val &= ~(0xf << (4 + shift));
+		for (delay_ns = 0; delay_ns < TIMING_DELAY_INPUT_MAX; delay_ns++) {
+			fread_timing_val &= ~(0xfu << (4 + shift));
 			fread_timing_val |= delay_ns << (4 + shift);
 
 			writel(fread_timing_val, TIMING_REG_AST2600(chip));
@@ -1070,18 +1419,28 @@ static int aspeed_spi_ast2600_calibrate(struct aspeed_spi_chip *chip, u32 hdiv,
 				"  * [%08x] %d HCLK delay, DI delay %d.%dns : %s",
 				fread_timing_val, hcycle, (delay_ns + 1) / 2,
 				(delay_ns + 1) & 1 ? 5 : 5, pass ? "PASS" : "FAIL");
-			/*
-			 * TODO: This is optimistic. We should look
-			 * for a working interval and save the middle
-			 * value in the read timing register.
-			 */
+
 			if (pass)
-				return 0;
+				calib_res[hcycle][delay_ns + 1] = 1;
 		}
 	}
 
+	calib_point = aspeed_spi_ast2600_optimized_timing(6, 17, calib_res);
 	/* No good setting for this frequency */
-	return -1;
+	if (calib_point == 0)
+		return -1;
+
+	hcycle = calib_point / 17;
+	delay_ns = calib_point % 17;
+
+	fread_timing_val = (TIMING_DELAY_DI | hcycle | (delay_ns << 4)) << shift;
+
+	dev_dbg(aspi->dev, "timing val: %08x, final hcycle: %d, delay_ns: %d\n",
+		fread_timing_val, hcycle, delay_ns);
+
+	writel(fread_timing_val, TIMING_REG_AST2600(chip));
+
+	return 0;
 }
 
 /*
@@ -1095,10 +1454,13 @@ static const struct aspeed_spi_data ast2400_fmc_data = {
 	.timing	       = CE0_TIMING_COMPENSATION_REG,
 	.hclk_mask     = 0xfffff0ff,
 	.hdiv_max      = 1,
+	.min_window_size = 0x800000,
 	.calibrate     = aspeed_spi_calibrate,
+	.get_clk_div   = aspeed_get_clk_div_ast2400,
 	.segment_start = aspeed_spi_segment_start,
 	.segment_end   = aspeed_spi_segment_end,
 	.segment_reg   = aspeed_spi_segment_reg,
+	.adjust_window = aspeed_adjust_window_ast2400,
 };
 
 static const struct aspeed_spi_data ast2400_spi_data = {
@@ -1109,6 +1471,7 @@ static const struct aspeed_spi_data ast2400_spi_data = {
 	.timing	       = 0x14,
 	.hclk_mask     = 0xfffff0ff,
 	.hdiv_max      = 1,
+	.get_clk_div   = aspeed_get_clk_div_ast2400,
 	.calibrate     = aspeed_spi_calibrate,
 	/* No segment registers */
 };
@@ -1121,10 +1484,13 @@ static const struct aspeed_spi_data ast2500_fmc_data = {
 	.timing	       = CE0_TIMING_COMPENSATION_REG,
 	.hclk_mask     = 0xffffd0ff,
 	.hdiv_max      = 1,
+	.min_window_size = 0x800000,
+	.get_clk_div   = aspeed_get_clk_div_ast2500,
 	.calibrate     = aspeed_spi_calibrate,
 	.segment_start = aspeed_spi_segment_start,
 	.segment_end   = aspeed_spi_segment_end,
 	.segment_reg   = aspeed_spi_segment_reg,
+	.adjust_window = aspeed_adjust_window_ast2500,
 };
 
 static const struct aspeed_spi_data ast2500_spi_data = {
@@ -1135,10 +1501,13 @@ static const struct aspeed_spi_data ast2500_spi_data = {
 	.timing	       = CE0_TIMING_COMPENSATION_REG,
 	.hclk_mask     = 0xffffd0ff,
 	.hdiv_max      = 1,
+	.min_window_size = 0x800000,
+	.get_clk_div   = aspeed_get_clk_div_ast2500,
 	.calibrate     = aspeed_spi_calibrate,
 	.segment_start = aspeed_spi_segment_start,
 	.segment_end   = aspeed_spi_segment_end,
 	.segment_reg   = aspeed_spi_segment_reg,
+	.adjust_window = aspeed_adjust_window_ast2500,
 };
 
 static const struct aspeed_spi_data ast2600_fmc_data = {
@@ -1150,10 +1519,13 @@ static const struct aspeed_spi_data ast2600_fmc_data = {
 	.timing	       = CE0_TIMING_COMPENSATION_REG,
 	.hclk_mask     = 0xf0fff0ff,
 	.hdiv_max      = 2,
+	.min_window_size = 0x200000,
+	.get_clk_div   = aspeed_get_clk_div_ast2600,
 	.calibrate     = aspeed_spi_ast2600_calibrate,
 	.segment_start = aspeed_spi_segment_ast2600_start,
 	.segment_end   = aspeed_spi_segment_ast2600_end,
 	.segment_reg   = aspeed_spi_segment_ast2600_reg,
+	.adjust_window = aspeed_adjust_window_ast2600,
 };
 
 static const struct aspeed_spi_data ast2600_spi_data = {
@@ -1165,10 +1537,47 @@ static const struct aspeed_spi_data ast2600_spi_data = {
 	.timing	       = CE0_TIMING_COMPENSATION_REG,
 	.hclk_mask     = 0xf0fff0ff,
 	.hdiv_max      = 2,
+	.min_window_size = 0x200000,
+	.get_clk_div   = aspeed_get_clk_div_ast2600,
 	.calibrate     = aspeed_spi_ast2600_calibrate,
 	.segment_start = aspeed_spi_segment_ast2600_start,
 	.segment_end   = aspeed_spi_segment_ast2600_end,
 	.segment_reg   = aspeed_spi_segment_ast2600_reg,
+	.adjust_window = aspeed_adjust_window_ast2600,
+};
+
+static const struct aspeed_spi_data ast2700_fmc_data = {
+	.max_cs	       = 3,
+	.hastype       = false,
+	.mode_bits     = SPI_RX_QUAD | SPI_TX_QUAD,
+	.we0	       = 16,
+	.ctl0	       = CE0_CTRL_REG,
+	.timing	       = CE0_TIMING_COMPENSATION_REG,
+	.hclk_mask     = 0xf0fff0ff,
+	.hdiv_max      = 2,
+	.min_window_size = 0x10000,
+	.get_clk_div   = aspeed_get_clk_div_ast2600,
+	.calibrate     = aspeed_spi_ast2600_calibrate,
+	.segment_start = aspeed_spi_segment_ast2700_start,
+	.segment_end   = aspeed_spi_segment_ast2700_end,
+	.segment_reg   = aspeed_spi_segment_ast2700_reg,
+};
+
+static const struct aspeed_spi_data ast2700_spi_data = {
+	.max_cs	       = 2,
+	.hastype       = false,
+	.mode_bits     = SPI_RX_QUAD | SPI_TX_QUAD,
+	.we0	       = 16,
+	.ctl0	       = CE0_CTRL_REG,
+	.timing	       = CE0_TIMING_COMPENSATION_REG,
+	.hclk_mask     = 0xf0fff0ff,
+	.hdiv_max      = 2,
+	.min_window_size = 0x10000,
+	.get_clk_div   = aspeed_get_clk_div_ast2600,
+	.calibrate     = aspeed_spi_ast2600_calibrate,
+	.segment_start = aspeed_spi_segment_ast2700_start,
+	.segment_end   = aspeed_spi_segment_ast2700_end,
+	.segment_reg   = aspeed_spi_segment_ast2700_reg,
 };
 
 static const struct of_device_id aspeed_spi_matches[] = {
@@ -1178,6 +1587,8 @@ static const struct of_device_id aspeed_spi_matches[] = {
 	{ .compatible = "aspeed,ast2500-spi", .data = &ast2500_spi_data },
 	{ .compatible = "aspeed,ast2600-fmc", .data = &ast2600_fmc_data },
 	{ .compatible = "aspeed,ast2600-spi", .data = &ast2600_spi_data },
+	{ .compatible = "aspeed,ast2700-fmc", .data = &ast2700_fmc_data },
+	{ .compatible = "aspeed,ast2700-spi", .data = &ast2700_spi_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, aspeed_spi_matches);
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index 2e3c62f..4c549f1 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -582,8 +582,8 @@ static int bcm63xx_spi_probe(struct platform_device *pdev)
 	host->auto_runtime_pm = true;
 	bs->msg_type_shift = bs->reg_offsets[SPI_MSG_TYPE_SHIFT];
 	bs->msg_ctl_width = bs->reg_offsets[SPI_MSG_CTL_WIDTH];
-	bs->tx_io = (u8 *)(bs->regs + bs->reg_offsets[SPI_MSG_DATA]);
-	bs->rx_io = (const u8 *)(bs->regs + bs->reg_offsets[SPI_RX_DATA]);
+	bs->tx_io = bs->regs + bs->reg_offsets[SPI_MSG_DATA];
+	bs->rx_io = bs->regs + bs->reg_offsets[SPI_RX_DATA];
 
 	/* Initialize hardware */
 	ret = clk_prepare_enable(bs->clk);
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 5ae09b2..47054da 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -109,6 +109,7 @@
  * @rxbuf:		Pointer to the RX buffer
  * @tx_bytes:		Number of bytes left to transfer
  * @rx_bytes:		Number of bytes requested
+ * @n_bytes:		Number of bytes per word
  * @dev_busy:		Device busy flag
  * @is_decoded_cs:	Flag for decoder property set or not
  * @tx_fifo_depth:	Depth of the TX FIFO
@@ -120,16 +121,24 @@ struct cdns_spi {
 	struct clk *pclk;
 	unsigned int clk_rate;
 	u32 speed_hz;
-	const u8 *txbuf;
-	u8 *rxbuf;
+	const void *txbuf;
+	void *rxbuf;
 	int tx_bytes;
 	int rx_bytes;
+	u8 n_bytes;
 	u8 dev_busy;
 	u32 is_decoded_cs;
 	unsigned int tx_fifo_depth;
 	struct reset_control *rstc;
 };
 
+enum cdns_spi_frame_n_bytes {
+	CDNS_SPI_N_BYTES_NULL = 0,
+	CDNS_SPI_N_BYTES_U8 = 1,
+	CDNS_SPI_N_BYTES_U16 = 2,
+	CDNS_SPI_N_BYTES_U32 = 4
+};
+
 /* Macros for the SPI controller read/write */
 static inline u32 cdns_spi_read(struct cdns_spi *xspi, u32 offset)
 {
@@ -305,6 +314,78 @@ static int cdns_spi_setup_transfer(struct spi_device *spi,
 	return 0;
 }
 
+static u8 cdns_spi_n_bytes(struct spi_transfer *transfer)
+{
+	if (transfer->bits_per_word <= 8)
+		return CDNS_SPI_N_BYTES_U8;
+	else if (transfer->bits_per_word <= 16)
+		return CDNS_SPI_N_BYTES_U16;
+	else
+		return CDNS_SPI_N_BYTES_U32;
+}
+
+static inline void cdns_spi_reader(struct cdns_spi *xspi)
+{
+	u32 rxw = 0;
+
+	if (xspi->rxbuf && !IS_ALIGNED((uintptr_t)xspi->rxbuf, xspi->n_bytes)) {
+		pr_err("%s: rxbuf address is not aligned for %d bytes\n",
+		       __func__, xspi->n_bytes);
+		return;
+	}
+
+	rxw = cdns_spi_read(xspi, CDNS_SPI_RXD);
+	if (xspi->rxbuf) {
+		switch (xspi->n_bytes) {
+		case CDNS_SPI_N_BYTES_U8:
+			*(u8 *)xspi->rxbuf = rxw;
+			break;
+		case CDNS_SPI_N_BYTES_U16:
+			*(u16 *)xspi->rxbuf = rxw;
+			break;
+		case CDNS_SPI_N_BYTES_U32:
+			*(u32 *)xspi->rxbuf = rxw;
+			break;
+		default:
+			pr_err("%s invalid n_bytes %d\n", __func__,
+			       xspi->n_bytes);
+			return;
+		}
+		xspi->rxbuf = (u8 *)xspi->rxbuf + xspi->n_bytes;
+	}
+}
+
+static inline void cdns_spi_writer(struct cdns_spi *xspi)
+{
+	u32 txw = 0;
+
+	if (xspi->txbuf && !IS_ALIGNED((uintptr_t)xspi->txbuf, xspi->n_bytes)) {
+		pr_err("%s: txbuf address is not aligned for %d bytes\n",
+		       __func__, xspi->n_bytes);
+		return;
+	}
+
+	if (xspi->txbuf) {
+		switch (xspi->n_bytes) {
+		case CDNS_SPI_N_BYTES_U8:
+			txw = *(u8 *)xspi->txbuf;
+			break;
+		case CDNS_SPI_N_BYTES_U16:
+			txw = *(u16 *)xspi->txbuf;
+			break;
+		case CDNS_SPI_N_BYTES_U32:
+			txw = *(u32 *)xspi->txbuf;
+			break;
+		default:
+			pr_err("%s invalid n_bytes %d\n", __func__,
+			       xspi->n_bytes);
+			return;
+		}
+		cdns_spi_write(xspi, CDNS_SPI_TXD, txw);
+		xspi->txbuf = (u8 *)xspi->txbuf + xspi->n_bytes;
+	}
+}
+
 /**
  * cdns_spi_process_fifo - Fills the TX FIFO, and drain the RX FIFO
  * @xspi:	Pointer to the cdns_spi structure
@@ -321,23 +402,14 @@ static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx)
 
 	while (ntx || nrx) {
 		if (nrx) {
-			u8 data = cdns_spi_read(xspi, CDNS_SPI_RXD);
-
-			if (xspi->rxbuf)
-				*xspi->rxbuf++ = data;
-
+			cdns_spi_reader(xspi);
 			nrx--;
 		}
 
 		if (ntx) {
-			if (xspi->txbuf)
-				cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
-			else
-				cdns_spi_write(xspi, CDNS_SPI_TXD, 0);
-
+			cdns_spi_writer(xspi);
 			ntx--;
 		}
-
 	}
 }
 
@@ -454,6 +526,10 @@ static int cdns_transfer_one(struct spi_controller *ctlr,
 	if (cdns_spi_read(xspi, CDNS_SPI_ISR) & CDNS_SPI_IXR_TXFULL)
 		udelay(10);
 
+	xspi->n_bytes = cdns_spi_n_bytes(transfer);
+	xspi->tx_bytes = DIV_ROUND_UP(xspi->tx_bytes, xspi->n_bytes);
+	xspi->rx_bytes = DIV_ROUND_UP(xspi->rx_bytes, xspi->n_bytes);
+
 	cdns_spi_process_fifo(xspi, xspi->tx_fifo_depth, 0);
 
 	cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT);
@@ -654,6 +730,9 @@ static int cdns_spi_probe(struct platform_device *pdev)
 	ctlr->mode_bits = SPI_CPOL | SPI_CPHA;
 	ctlr->bits_per_word_mask = SPI_BPW_MASK(8);
 
+	if (of_device_is_compatible(pdev->dev.of_node, "cix,sky1-spi-r1p6"))
+		ctlr->bits_per_word_mask |= SPI_BPW_MASK(16) | SPI_BPW_MASK(32);
+
 	if (!spi_controller_is_target(ctlr)) {
 		ctlr->mode_bits |=  SPI_CS_HIGH;
 		ctlr->set_cs = cdns_spi_chipselect;
@@ -797,6 +876,7 @@ static const struct dev_pm_ops cdns_spi_dev_pm_ops = {
 
 static const struct of_device_id cdns_spi_of_match[] = {
 	{ .compatible = "xlnx,zynq-spi-r1p6" },
+	{ .compatible = "cix,sky1-spi-r1p6" },
 	{ .compatible = "cdns,spi-r1p6" },
 	{ /* end of table */ }
 };
diff --git a/drivers/spi/spi-ch341.c b/drivers/spi/spi-ch341.c
index 46bc208..79d2f9a 100644
--- a/drivers/spi/spi-ch341.c
+++ b/drivers/spi/spi-ch341.c
@@ -78,7 +78,7 @@ static int ch341_transfer_one(struct spi_controller *host,
 
 	ch341->tx_buf[0] = CH341A_CMD_SPI_STREAM;
 
-	memcpy(ch341->tx_buf + 1, trans->tx_buf, len);
+	memcpy(ch341->tx_buf + 1, trans->tx_buf, len - 1);
 
 	ret = usb_bulk_msg(ch341->udev, ch341->write_pipe, ch341->tx_buf, len,
 			   NULL, CH341_DEFAULT_TIMEOUT);
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index a299344..21a14e8 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -9,6 +9,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/delay.h>
+#include <linux/platform_data/edma.h>
 #include <linux/platform_device.h>
 #include <linux/err.h>
 #include <linux/clk.h>
@@ -19,8 +20,6 @@
 #include <linux/spi/spi_bitbang.h>
 #include <linux/slab.h>
 
-#include <linux/platform_data/spi-davinci.h>
-
 #define CS_DEFAULT	0xFF
 
 #define SPIFMT_PHASE_MASK	BIT(16)
@@ -98,8 +97,69 @@
 #define SPIDEF		0x4c
 #define SPIFMT0		0x50
 
+#define SPI_IO_TYPE_POLL	1
+#define SPI_IO_TYPE_DMA		2
+
 #define DMA_MIN_BYTES	16
 
+enum {
+	SPI_VERSION_1, /* For DM355/DM365/DM6467 */
+	SPI_VERSION_2, /* For DA8xx */
+};
+
+/**
+ * struct davinci_spi_platform_data - Platform data for SPI master device on DaVinci
+ *
+ * @version:	version of the SPI IP. Different DaVinci devices have slightly
+ *		varying versions of the same IP.
+ * @num_chipselect: number of chipselects supported by this SPI master
+ * @intr_line:	interrupt line used to connect the SPI IP to the ARM interrupt
+ *		controller withn the SoC. Possible values are 0 and 1.
+ * @prescaler_limit: max clock prescaler value
+ * @cshold_bug:	set this to true if the SPI controller on your chip requires
+ *		a write to CSHOLD bit in between transfers (like in DM355).
+ * @dma_event_q: DMA event queue to use if SPI_IO_TYPE_DMA is used for any
+ *		device on the bus.
+ */
+struct davinci_spi_platform_data {
+	u8			version;
+	u8			num_chipselect;
+	u8			intr_line;
+	u8			prescaler_limit;
+	bool			cshold_bug;
+	enum dma_event_q	dma_event_q;
+};
+
+/**
+ * struct davinci_spi_config - Per-chip-select configuration for SPI slave devices
+ *
+ * @wdelay:	amount of delay between transmissions. Measured in number of
+ *		SPI module clocks.
+ * @odd_parity:	polarity of parity flag at the end of transmit data stream.
+ *		0 - odd parity, 1 - even parity.
+ * @parity_enable: enable transmission of parity at end of each transmit
+ *		data stream.
+ * @io_type:	type of IO transfer. Choose between polled, interrupt and DMA.
+ * @timer_disable: disable chip-select timers (setup and hold)
+ * @c2tdelay:	chip-select setup time. Measured in number of SPI module clocks.
+ * @t2cdelay:	chip-select hold time. Measured in number of SPI module clocks.
+ * @t2edelay:	transmit data finished to SPI ENAn pin inactive time. Measured
+ *		in number of SPI clocks.
+ * @c2edelay:	chip-select active to SPI ENAn signal active time. Measured in
+ *		number of SPI clocks.
+ */
+struct davinci_spi_config {
+	u8	wdelay;
+	u8	odd_parity;
+	u8	parity_enable;
+	u8	io_type;
+	u8	timer_disable;
+	u8	c2tdelay;
+	u8	t2cdelay;
+	u8	t2edelay;
+	u8	c2edelay;
+};
+
 /* SPI Controller driver's private data. */
 struct davinci_spi {
 	struct spi_bitbang	bitbang;
diff --git a/drivers/spi/spi-dw-bt1.c b/drivers/spi/spi-dw-bt1.c
index 4a5be81..91642e0 100644
--- a/drivers/spi/spi-dw-bt1.c
+++ b/drivers/spi/spi-dw-bt1.c
@@ -288,7 +288,7 @@ static int dw_spi_bt1_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(&pdev->dev);
 
-	ret = dw_spi_add_host(&pdev->dev, dws);
+	ret = dw_spi_add_controller(&pdev->dev, dws);
 	if (ret) {
 		pm_runtime_disable(&pdev->dev);
 		return ret;
@@ -303,7 +303,7 @@ static void dw_spi_bt1_remove(struct platform_device *pdev)
 {
 	struct dw_spi_bt1 *dwsbt1 = platform_get_drvdata(pdev);
 
-	dw_spi_remove_host(&dwsbt1->dws);
+	dw_spi_remove_controller(&dwsbt1->dws);
 
 	pm_runtime_disable(&pdev->dev);
 }
diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c
index b3b883c..9ebf244 100644
--- a/drivers/spi/spi-dw-core.c
+++ b/drivers/spi/spi-dw-core.c
@@ -63,7 +63,7 @@ static void dw_spi_debugfs_init(struct dw_spi *dws)
 {
 	char name[32];
 
-	snprintf(name, 32, "dw_spi%d", dws->host->bus_num);
+	snprintf(name, 32, "dw_spi%d", dws->ctlr->bus_num);
 	dws->debugfs = debugfs_create_dir(name, NULL);
 
 	dws->regset.regs = dw_spi_dbgfs_regs;
@@ -185,25 +185,25 @@ int dw_spi_check_status(struct dw_spi *dws, bool raw)
 		irq_status = dw_readl(dws, DW_SPI_ISR);
 
 	if (irq_status & DW_SPI_INT_RXOI) {
-		dev_err(&dws->host->dev, "RX FIFO overflow detected\n");
+		dev_err(&dws->ctlr->dev, "RX FIFO overflow detected\n");
 		ret = -EIO;
 	}
 
 	if (irq_status & DW_SPI_INT_RXUI) {
-		dev_err(&dws->host->dev, "RX FIFO underflow detected\n");
+		dev_err(&dws->ctlr->dev, "RX FIFO underflow detected\n");
 		ret = -EIO;
 	}
 
 	if (irq_status & DW_SPI_INT_TXOI) {
-		dev_err(&dws->host->dev, "TX FIFO overflow detected\n");
+		dev_err(&dws->ctlr->dev, "TX FIFO overflow detected\n");
 		ret = -EIO;
 	}
 
 	/* Generically handle the erroneous situation */
 	if (ret) {
 		dw_spi_reset_chip(dws);
-		if (dws->host->cur_msg)
-			dws->host->cur_msg->status = ret;
+		if (dws->ctlr->cur_msg)
+			dws->ctlr->cur_msg->status = ret;
 	}
 
 	return ret;
@@ -215,7 +215,7 @@ static irqreturn_t dw_spi_transfer_handler(struct dw_spi *dws)
 	u16 irq_status = dw_readl(dws, DW_SPI_ISR);
 
 	if (dw_spi_check_status(dws, false)) {
-		spi_finalize_current_transfer(dws->host);
+		spi_finalize_current_transfer(dws->ctlr);
 		return IRQ_HANDLED;
 	}
 
@@ -229,7 +229,7 @@ static irqreturn_t dw_spi_transfer_handler(struct dw_spi *dws)
 	dw_reader(dws);
 	if (!dws->rx_len) {
 		dw_spi_mask_intr(dws, 0xff);
-		spi_finalize_current_transfer(dws->host);
+		spi_finalize_current_transfer(dws->ctlr);
 	} else if (dws->rx_len <= dw_readl(dws, DW_SPI_RXFTLR)) {
 		dw_writel(dws, DW_SPI_RXFTLR, dws->rx_len - 1);
 	}
@@ -250,14 +250,14 @@ static irqreturn_t dw_spi_transfer_handler(struct dw_spi *dws)
 
 static irqreturn_t dw_spi_irq(int irq, void *dev_id)
 {
-	struct spi_controller *host = dev_id;
-	struct dw_spi *dws = spi_controller_get_devdata(host);
+	struct spi_controller *ctlr = dev_id;
+	struct dw_spi *dws = spi_controller_get_devdata(ctlr);
 	u16 irq_status = dw_readl(dws, DW_SPI_ISR) & DW_SPI_INT_MASK;
 
 	if (!irq_status)
 		return IRQ_NONE;
 
-	if (!host->cur_msg) {
+	if (!ctlr->cur_msg) {
 		dw_spi_mask_intr(dws, 0xff);
 		return IRQ_HANDLED;
 	}
@@ -332,6 +332,9 @@ void dw_spi_update_config(struct dw_spi *dws, struct spi_device *spi,
 
 	dw_writel(dws, DW_SPI_CTRLR0, cr0);
 
+	if (spi_controller_is_target(dws->ctlr))
+		return;
+
 	if (cfg->tmode == DW_SPI_CTRLR0_TMOD_EPROMREAD ||
 	    cfg->tmode == DW_SPI_CTRLR0_TMOD_RO)
 		dw_writel(dws, DW_SPI_CTRLR1, cfg->ndf ? cfg->ndf - 1 : 0);
@@ -410,11 +413,11 @@ static int dw_spi_poll_transfer(struct dw_spi *dws,
 	return 0;
 }
 
-static int dw_spi_transfer_one(struct spi_controller *host,
+static int dw_spi_transfer_one(struct spi_controller *ctlr,
 			       struct spi_device *spi,
 			       struct spi_transfer *transfer)
 {
-	struct dw_spi *dws = spi_controller_get_devdata(host);
+	struct dw_spi *dws = spi_controller_get_devdata(ctlr);
 	struct dw_spi_cfg cfg = {
 		.tmode = DW_SPI_CTRLR0_TMOD_TR,
 		.dfs = transfer->bits_per_word,
@@ -439,7 +442,7 @@ static int dw_spi_transfer_one(struct spi_controller *host,
 	transfer->effective_speed_hz = dws->current_freq;
 
 	/* Check if current transfer is a DMA transaction */
-	dws->dma_mapped = spi_xfer_is_dma_mapped(host, spi, transfer);
+	dws->dma_mapped = spi_xfer_is_dma_mapped(ctlr, spi, transfer);
 
 	/* For poll mode just disable all interrupts */
 	dw_spi_mask_intr(dws, 0xff);
@@ -462,10 +465,9 @@ static int dw_spi_transfer_one(struct spi_controller *host,
 	return 1;
 }
 
-static void dw_spi_handle_err(struct spi_controller *host,
-			      struct spi_message *msg)
+static inline void dw_spi_abort(struct spi_controller *ctlr)
 {
-	struct dw_spi *dws = spi_controller_get_devdata(host);
+	struct dw_spi *dws = spi_controller_get_devdata(ctlr);
 
 	if (dws->dma_mapped)
 		dws->dma_ops->dma_stop(dws);
@@ -473,6 +475,19 @@ static void dw_spi_handle_err(struct spi_controller *host,
 	dw_spi_reset_chip(dws);
 }
 
+static void dw_spi_handle_err(struct spi_controller *ctlr,
+			      struct spi_message *msg)
+{
+	dw_spi_abort(ctlr);
+}
+
+static int dw_spi_target_abort(struct spi_controller *ctlr)
+{
+	dw_spi_abort(ctlr);
+
+	return 0;
+}
+
 static int dw_spi_adjust_mem_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 {
 	if (op->data.dir == SPI_MEM_DATA_IN)
@@ -574,7 +589,7 @@ static int dw_spi_write_then_read(struct dw_spi *dws, struct spi_device *spi)
 	while (len) {
 		entries = readl_relaxed(dws->regs + DW_SPI_TXFLR);
 		if (!entries) {
-			dev_err(&dws->host->dev, "CS de-assertion on Tx\n");
+			dev_err(&dws->ctlr->dev, "CS de-assertion on Tx\n");
 			return -EIO;
 		}
 		room = min(dws->fifo_len - entries, len);
@@ -594,7 +609,7 @@ static int dw_spi_write_then_read(struct dw_spi *dws, struct spi_device *spi)
 		if (!entries) {
 			sts = readl_relaxed(dws->regs + DW_SPI_RISR);
 			if (sts & DW_SPI_INT_RXOI) {
-				dev_err(&dws->host->dev, "FIFO overflow on Rx\n");
+				dev_err(&dws->ctlr->dev, "FIFO overflow on Rx\n");
 				return -EIO;
 			}
 			continue;
@@ -635,7 +650,7 @@ static int dw_spi_wait_mem_op_done(struct dw_spi *dws)
 		spi_delay_exec(&delay, NULL);
 
 	if (retry < 0) {
-		dev_err(&dws->host->dev, "Mem op hanged up\n");
+		dev_err(&dws->ctlr->dev, "Mem op hanged up\n");
 		return -EIO;
 	}
 
@@ -834,18 +849,23 @@ static void dw_spi_hw_init(struct device *dev, struct dw_spi *dws)
 			DW_SPI_GET_BYTE(dws->ver, 1));
 	}
 
-	/*
-	 * Try to detect the number of native chip-selects if the platform
-	 * driver didn't set it up. There can be up to 16 lines configured.
-	 */
-	if (!dws->num_cs) {
-		u32 ser;
+	if (spi_controller_is_target(dws->ctlr)) {
+		/* There is only one CS input signal in target mode */
+		dws->num_cs = 1;
+	} else {
+		/*
+		 * Try to detect the number of native chip-selects if the platform
+		 * driver didn't set it up. There can be up to 16 lines configured.
+		 */
+		if (!dws->num_cs) {
+			u32 ser;
 
-		dw_writel(dws, DW_SPI_SER, 0xffff);
-		ser = dw_readl(dws, DW_SPI_SER);
-		dw_writel(dws, DW_SPI_SER, 0);
+			dw_writel(dws, DW_SPI_SER, 0xffff);
+			ser = dw_readl(dws, DW_SPI_SER);
+			dw_writel(dws, DW_SPI_SER, 0);
 
-		dws->num_cs = hweight16(ser);
+			dws->num_cs = hweight16(ser);
+		}
 	}
 
 	/*
@@ -898,60 +918,72 @@ static const struct spi_controller_mem_caps dw_spi_mem_caps = {
 	.per_op_freq = true,
 };
 
-int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
+int dw_spi_add_controller(struct device *dev, struct dw_spi *dws)
 {
-	struct spi_controller *host;
+	struct spi_controller *ctlr;
+	bool target;
 	int ret;
 
 	if (!dws)
 		return -EINVAL;
 
-	host = spi_alloc_host(dev, 0);
-	if (!host)
+	target = device_property_read_bool(dev, "spi-slave");
+	if (target)
+		ctlr = spi_alloc_target(dev, 0);
+	else
+		ctlr = spi_alloc_host(dev, 0);
+
+	if (!ctlr)
 		return -ENOMEM;
 
-	device_set_node(&host->dev, dev_fwnode(dev));
+	device_set_node(&ctlr->dev, dev_fwnode(dev));
 
-	dws->host = host;
+	dws->ctlr = ctlr;
 	dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
 
-	spi_controller_set_devdata(host, dws);
+	spi_controller_set_devdata(ctlr, dws);
 
 	/* Basic HW init */
 	dw_spi_hw_init(dev, dws);
 
 	ret = request_irq(dws->irq, dw_spi_irq, IRQF_SHARED, dev_name(dev),
-			  host);
+			  ctlr);
 	if (ret < 0 && ret != -ENOTCONN) {
 		dev_err(dev, "can not get IRQ\n");
-		goto err_free_host;
+		goto err_free_ctlr;
 	}
 
 	dw_spi_init_mem_ops(dws);
 
-	host->use_gpio_descriptors = true;
-	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LOOP;
+	ctlr->mode_bits = SPI_CPOL | SPI_CPHA;
 	if (dws->caps & DW_SPI_CAP_DFS32)
-		host->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
-	else
-		host->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
-	host->bus_num = dws->bus_num;
-	host->num_chipselect = dws->num_cs;
-	host->setup = dw_spi_setup;
-	host->cleanup = dw_spi_cleanup;
-	if (dws->set_cs)
-		host->set_cs = dws->set_cs;
+		ctlr->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	else
-		host->set_cs = dw_spi_set_cs;
-	host->transfer_one = dw_spi_transfer_one;
-	host->handle_err = dw_spi_handle_err;
-	if (dws->mem_ops.exec_op) {
-		host->mem_ops = &dws->mem_ops;
-		host->mem_caps = &dw_spi_mem_caps;
+		ctlr->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
+	ctlr->bus_num = dws->bus_num;
+	ctlr->num_chipselect = dws->num_cs;
+	ctlr->setup = dw_spi_setup;
+	ctlr->cleanup = dw_spi_cleanup;
+	ctlr->transfer_one = dw_spi_transfer_one;
+	ctlr->handle_err = dw_spi_handle_err;
+	ctlr->auto_runtime_pm = true;
+
+	if (!target) {
+		ctlr->use_gpio_descriptors = true;
+		ctlr->mode_bits |= SPI_LOOP;
+		if (dws->set_cs)
+			ctlr->set_cs = dws->set_cs;
+		else
+			ctlr->set_cs = dw_spi_set_cs;
+		if (dws->mem_ops.exec_op) {
+			ctlr->mem_ops = &dws->mem_ops;
+			ctlr->mem_caps = &dw_spi_mem_caps;
+		}
+		ctlr->max_speed_hz = dws->max_freq;
+		ctlr->flags = SPI_CONTROLLER_GPIO_SS;
+	} else {
+		ctlr->target_abort = dw_spi_target_abort;
 	}
-	host->max_speed_hz = dws->max_freq;
-	host->flags = SPI_CONTROLLER_GPIO_SS;
-	host->auto_runtime_pm = true;
 
 	/* Get default rx sample delay */
 	device_property_read_u32(dev, "rx-sample-delay-ns",
@@ -964,14 +996,14 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 		} else if (ret) {
 			dev_warn(dev, "DMA init failed\n");
 		} else {
-			host->can_dma = dws->dma_ops->can_dma;
-			host->flags |= SPI_CONTROLLER_MUST_TX;
+			ctlr->can_dma = dws->dma_ops->can_dma;
+			ctlr->flags |= SPI_CONTROLLER_MUST_TX;
 		}
 	}
 
-	ret = spi_register_controller(host);
+	ret = spi_register_controller(ctlr);
 	if (ret) {
-		dev_err_probe(dev, ret, "problem registering spi host\n");
+		dev_err_probe(dev, ret, "problem registering spi controller\n");
 		goto err_dma_exit;
 	}
 
@@ -983,47 +1015,47 @@ err_dma_exit:
 		dws->dma_ops->dma_exit(dws);
 	dw_spi_enable_chip(dws, 0);
 err_free_irq:
-	free_irq(dws->irq, host);
-err_free_host:
-	spi_controller_put(host);
+	free_irq(dws->irq, ctlr);
+err_free_ctlr:
+	spi_controller_put(ctlr);
 	return ret;
 }
-EXPORT_SYMBOL_NS_GPL(dw_spi_add_host, "SPI_DW_CORE");
+EXPORT_SYMBOL_NS_GPL(dw_spi_add_controller, "SPI_DW_CORE");
 
-void dw_spi_remove_host(struct dw_spi *dws)
+void dw_spi_remove_controller(struct dw_spi *dws)
 {
 	dw_spi_debugfs_remove(dws);
 
-	spi_unregister_controller(dws->host);
+	spi_unregister_controller(dws->ctlr);
 
 	if (dws->dma_ops && dws->dma_ops->dma_exit)
 		dws->dma_ops->dma_exit(dws);
 
 	dw_spi_shutdown_chip(dws);
 
-	free_irq(dws->irq, dws->host);
+	free_irq(dws->irq, dws->ctlr);
 }
-EXPORT_SYMBOL_NS_GPL(dw_spi_remove_host, "SPI_DW_CORE");
+EXPORT_SYMBOL_NS_GPL(dw_spi_remove_controller, "SPI_DW_CORE");
 
-int dw_spi_suspend_host(struct dw_spi *dws)
+int dw_spi_suspend_controller(struct dw_spi *dws)
 {
 	int ret;
 
-	ret = spi_controller_suspend(dws->host);
+	ret = spi_controller_suspend(dws->ctlr);
 	if (ret)
 		return ret;
 
 	dw_spi_shutdown_chip(dws);
 	return 0;
 }
-EXPORT_SYMBOL_NS_GPL(dw_spi_suspend_host, "SPI_DW_CORE");
+EXPORT_SYMBOL_NS_GPL(dw_spi_suspend_controller, "SPI_DW_CORE");
 
-int dw_spi_resume_host(struct dw_spi *dws)
+int dw_spi_resume_controller(struct dw_spi *dws)
 {
-	dw_spi_hw_init(&dws->host->dev, dws);
-	return spi_controller_resume(dws->host);
+	dw_spi_hw_init(&dws->ctlr->dev, dws);
+	return spi_controller_resume(dws->ctlr);
 }
-EXPORT_SYMBOL_NS_GPL(dw_spi_resume_host, "SPI_DW_CORE");
+EXPORT_SYMBOL_NS_GPL(dw_spi_resume_controller, "SPI_DW_CORE");
 
 MODULE_AUTHOR("Feng Tang <feng.tang@intel.com>");
 MODULE_DESCRIPTION("Driver for DesignWare SPI controller core");
diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c
index b5bed02..65adec7 100644
--- a/drivers/spi/spi-dw-dma.c
+++ b/drivers/spi/spi-dw-dma.c
@@ -139,8 +139,8 @@ static int dw_spi_dma_init_mfld(struct device *dev, struct dw_spi *dws)
 	if (!dws->txchan)
 		goto free_rxchan;
 
-	dws->host->dma_rx = dws->rxchan;
-	dws->host->dma_tx = dws->txchan;
+	dws->ctlr->dma_rx = dws->rxchan;
+	dws->ctlr->dma_tx = dws->txchan;
 
 	init_completion(&dws->dma_completion);
 
@@ -183,8 +183,8 @@ static int dw_spi_dma_init_generic(struct device *dev, struct dw_spi *dws)
 		goto free_rxchan;
 	}
 
-	dws->host->dma_rx = dws->rxchan;
-	dws->host->dma_tx = dws->txchan;
+	dws->ctlr->dma_rx = dws->rxchan;
+	dws->ctlr->dma_tx = dws->txchan;
 
 	init_completion(&dws->dma_completion);
 
@@ -242,10 +242,10 @@ static enum dma_slave_buswidth dw_spi_dma_convert_width(u8 n_bytes)
 	}
 }
 
-static bool dw_spi_can_dma(struct spi_controller *host,
+static bool dw_spi_can_dma(struct spi_controller *ctlr,
 			   struct spi_device *spi, struct spi_transfer *xfer)
 {
-	struct dw_spi *dws = spi_controller_get_devdata(host);
+	struct dw_spi *dws = spi_controller_get_devdata(ctlr);
 	enum dma_slave_buswidth dma_bus_width;
 
 	if (xfer->len <= dws->fifo_len)
@@ -271,7 +271,7 @@ static int dw_spi_dma_wait(struct dw_spi *dws, unsigned int len, u32 speed)
 					 msecs_to_jiffies(ms));
 
 	if (ms == 0) {
-		dev_err(&dws->host->cur_msg->spi->dev,
+		dev_err(&dws->ctlr->cur_msg->spi->dev,
 			"DMA transaction timed out\n");
 		return -ETIMEDOUT;
 	}
@@ -299,7 +299,7 @@ static int dw_spi_dma_wait_tx_done(struct dw_spi *dws,
 		spi_delay_exec(&delay, xfer);
 
 	if (retry < 0) {
-		dev_err(&dws->host->dev, "Tx hanged up\n");
+		dev_err(&dws->ctlr->dev, "Tx hanged up\n");
 		return -EIO;
 	}
 
@@ -400,7 +400,7 @@ static int dw_spi_dma_wait_rx_done(struct dw_spi *dws)
 		spi_delay_exec(&delay, NULL);
 
 	if (retry < 0) {
-		dev_err(&dws->host->dev, "Rx hanged up\n");
+		dev_err(&dws->ctlr->dev, "Rx hanged up\n");
 		return -EIO;
 	}
 
@@ -656,13 +656,13 @@ static int dw_spi_dma_transfer(struct dw_spi *dws, struct spi_transfer *xfer)
 	if (ret)
 		return ret;
 
-	if (dws->host->cur_msg->status == -EINPROGRESS) {
+	if (dws->ctlr->cur_msg->status == -EINPROGRESS) {
 		ret = dw_spi_dma_wait_tx_done(dws, xfer);
 		if (ret)
 			return ret;
 	}
 
-	if (xfer->rx_buf && dws->host->cur_msg->status == -EINPROGRESS)
+	if (xfer->rx_buf && dws->ctlr->cur_msg->status == -EINPROGRESS)
 		ret = dw_spi_dma_wait_rx_done(dws);
 
 	return ret;
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index 7a51975..33239b4 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -321,11 +321,6 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 	struct dw_spi *dws;
 	int ret;
 
-	if (device_property_read_bool(&pdev->dev, "spi-slave")) {
-		dev_warn(&pdev->dev, "spi-slave is not yet supported\n");
-		return -ENODEV;
-	}
-
 	dwsmmio = devm_kzalloc(&pdev->dev, sizeof(struct dw_spi_mmio),
 			GFP_KERNEL);
 	if (!dwsmmio)
@@ -382,7 +377,7 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(&pdev->dev);
 
-	ret = dw_spi_add_host(&pdev->dev, dws);
+	ret = dw_spi_add_controller(&pdev->dev, dws);
 	if (ret)
 		goto out;
 
@@ -401,7 +396,7 @@ static void dw_spi_mmio_remove(struct platform_device *pdev)
 {
 	struct dw_spi_mmio *dwsmmio = platform_get_drvdata(pdev);
 
-	dw_spi_remove_host(&dwsmmio->dws);
+	dw_spi_remove_controller(&dwsmmio->dws);
 	pm_runtime_disable(&pdev->dev);
 	reset_control_assert(dwsmmio->rstc);
 }
diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c
index b32d664..72d9f5b 100644
--- a/drivers/spi/spi-dw-pci.c
+++ b/drivers/spi/spi-dw-pci.c
@@ -127,7 +127,7 @@ static int dw_spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *en
 		goto err_free_irq_vectors;
 	}
 
-	ret = dw_spi_add_host(&pdev->dev, dws);
+	ret = dw_spi_add_controller(&pdev->dev, dws);
 	if (ret)
 		goto err_free_irq_vectors;
 
@@ -156,7 +156,7 @@ static void dw_spi_pci_remove(struct pci_dev *pdev)
 	pm_runtime_forbid(&pdev->dev);
 	pm_runtime_get_noresume(&pdev->dev);
 
-	dw_spi_remove_host(dws);
+	dw_spi_remove_controller(dws);
 	pci_free_irq_vectors(pdev);
 }
 
@@ -165,14 +165,14 @@ static int dw_spi_pci_suspend(struct device *dev)
 {
 	struct dw_spi *dws = dev_get_drvdata(dev);
 
-	return dw_spi_suspend_host(dws);
+	return dw_spi_suspend_controller(dws);
 }
 
 static int dw_spi_pci_resume(struct device *dev)
 {
 	struct dw_spi *dws = dev_get_drvdata(dev);
 
-	return dw_spi_resume_host(dws);
+	return dw_spi_resume_controller(dws);
 }
 #endif
 
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index fc267c6..9cc79c5 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -142,14 +142,14 @@ struct dw_spi_dma_ops {
 	int (*dma_init)(struct device *dev, struct dw_spi *dws);
 	void (*dma_exit)(struct dw_spi *dws);
 	int (*dma_setup)(struct dw_spi *dws, struct spi_transfer *xfer);
-	bool (*can_dma)(struct spi_controller *host, struct spi_device *spi,
+	bool (*can_dma)(struct spi_controller *ctlr, struct spi_device *spi,
 			struct spi_transfer *xfer);
 	int (*dma_transfer)(struct dw_spi *dws, struct spi_transfer *xfer);
 	void (*dma_stop)(struct dw_spi *dws);
 };
 
 struct dw_spi {
-	struct spi_controller	*host;
+	struct spi_controller	*ctlr;
 
 	u32			ip;		/* Synopsys DW SSI IP-core ID */
 	u32			ver;		/* Synopsys component version */
@@ -288,10 +288,10 @@ extern void dw_spi_set_cs(struct spi_device *spi, bool enable);
 extern void dw_spi_update_config(struct dw_spi *dws, struct spi_device *spi,
 				 struct dw_spi_cfg *cfg);
 extern int dw_spi_check_status(struct dw_spi *dws, bool raw);
-extern int dw_spi_add_host(struct device *dev, struct dw_spi *dws);
-extern void dw_spi_remove_host(struct dw_spi *dws);
-extern int dw_spi_suspend_host(struct dw_spi *dws);
-extern int dw_spi_resume_host(struct dw_spi *dws);
+extern int dw_spi_add_controller(struct device *dev, struct dw_spi *dws);
+extern void dw_spi_remove_controller(struct dw_spi *dws);
+extern int dw_spi_suspend_controller(struct dw_spi *dws);
+extern int dw_spi_resume_controller(struct dw_spi *dws);
 
 #ifdef CONFIG_SPI_DW_DMA
 
diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c
index c887abb..a223b4b 100644
--- a/drivers/spi/spi-fsl-qspi.c
+++ b/drivers/spi/spi-fsl-qspi.c
@@ -36,6 +36,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_qos.h>
+#include <linux/reset.h>
 #include <linux/sizes.h>
 
 #include <linux/spi/spi.h>
@@ -196,11 +197,17 @@
  */
 #define QUADSPI_QUIRK_USE_TDH_SETTING	BIT(5)
 
+/*
+ * Do not disable the "qspi" clock when changing its rate.
+ */
+#define QUADSPI_QUIRK_SKIP_CLK_DISABLE	BIT(6)
+
 struct fsl_qspi_devtype_data {
 	unsigned int rxfifo;
 	unsigned int txfifo;
 	int invalid_mstrid;
 	unsigned int ahb_buf_size;
+	unsigned int sfa_size;
 	unsigned int quirks;
 	bool little_endian;
 };
@@ -261,12 +268,23 @@ static const struct fsl_qspi_devtype_data ls2080a_data = {
 	.little_endian = true,
 };
 
+static const struct fsl_qspi_devtype_data spacemit_k1_data = {
+	.rxfifo = SZ_128,
+	.txfifo = SZ_256,
+	.ahb_buf_size = SZ_512,
+	.sfa_size = SZ_1K,
+	.invalid_mstrid = QUADSPI_BUFXCR_INVALID_MSTRID,
+	.quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_SKIP_CLK_DISABLE,
+	.little_endian = true,
+};
+
 struct fsl_qspi {
 	void __iomem *iobase;
 	void __iomem *ahb_addr;
 	const struct fsl_qspi_devtype_data *devtype_data;
 	struct mutex lock;
 	struct completion c;
+	struct reset_control *resets;
 	struct clk *clk, *clk_en;
 	struct pm_qos_request pm_qos_req;
 	struct device *dev;
@@ -274,34 +292,39 @@ struct fsl_qspi {
 	u32 memmap_phy;
 };
 
-static inline int needs_swap_endian(struct fsl_qspi *q)
+static bool needs_swap_endian(struct fsl_qspi *q)
 {
-	return q->devtype_data->quirks & QUADSPI_QUIRK_SWAP_ENDIAN;
+	return !!(q->devtype_data->quirks & QUADSPI_QUIRK_SWAP_ENDIAN);
 }
 
-static inline int needs_4x_clock(struct fsl_qspi *q)
+static bool needs_4x_clock(struct fsl_qspi *q)
 {
-	return q->devtype_data->quirks & QUADSPI_QUIRK_4X_INT_CLK;
+	return !!(q->devtype_data->quirks & QUADSPI_QUIRK_4X_INT_CLK);
 }
 
-static inline int needs_fill_txfifo(struct fsl_qspi *q)
+static bool needs_fill_txfifo(struct fsl_qspi *q)
 {
-	return q->devtype_data->quirks & QUADSPI_QUIRK_TKT253890;
+	return !!(q->devtype_data->quirks & QUADSPI_QUIRK_TKT253890);
 }
 
-static inline int needs_wakeup_wait_mode(struct fsl_qspi *q)
+static bool needs_wakeup_wait_mode(struct fsl_qspi *q)
 {
-	return q->devtype_data->quirks & QUADSPI_QUIRK_TKT245618;
+	return !!(q->devtype_data->quirks & QUADSPI_QUIRK_TKT245618);
 }
 
-static inline int needs_amba_base_offset(struct fsl_qspi *q)
+static bool needs_amba_base_offset(struct fsl_qspi *q)
 {
 	return !(q->devtype_data->quirks & QUADSPI_QUIRK_BASE_INTERNAL);
 }
 
-static inline int needs_tdh_setting(struct fsl_qspi *q)
+static bool needs_tdh_setting(struct fsl_qspi *q)
+{
+	return !!(q->devtype_data->quirks & QUADSPI_QUIRK_USE_TDH_SETTING);
+}
+
+static bool needs_clk_disable(struct fsl_qspi *q)
 {
-	return q->devtype_data->quirks & QUADSPI_QUIRK_USE_TDH_SETTING;
+	return !(q->devtype_data->quirks & QUADSPI_QUIRK_SKIP_CLK_DISABLE);
 }
 
 /*
@@ -534,15 +557,18 @@ static void fsl_qspi_select_mem(struct fsl_qspi *q, struct spi_device *spi,
 	if (needs_4x_clock(q))
 		rate *= 4;
 
-	fsl_qspi_clk_disable_unprep(q);
+	if (needs_clk_disable(q))
+		fsl_qspi_clk_disable_unprep(q);
 
 	ret = clk_set_rate(q->clk, rate);
 	if (ret)
 		return;
 
-	ret = fsl_qspi_clk_prep_enable(q);
-	if (ret)
-		return;
+	if (needs_clk_disable(q)) {
+		ret = fsl_qspi_clk_prep_enable(q);
+		if (ret)
+			return;
+	}
 
 	q->selected = spi_get_chipselect(spi, 0);
 
@@ -722,6 +748,7 @@ static int fsl_qspi_default_setup(struct fsl_qspi *q)
 {
 	void __iomem *base = q->iobase;
 	u32 reg, addr_offset = 0;
+	u32 sfa_size;
 	int ret;
 
 	/* disable and unprepare clock to avoid glitch pass to controller */
@@ -780,17 +807,17 @@ static int fsl_qspi_default_setup(struct fsl_qspi *q)
 	 * In HW there can be a maximum of four chips on two buses with
 	 * two chip selects on each bus. We use four chip selects in SW
 	 * to differentiate between the four chips.
-	 * We use ahb_buf_size for each chip and set SFA1AD, SFA2AD, SFB1AD,
-	 * SFB2AD accordingly.
+	 *
+	 * By default we write the AHB buffer size to each chip, but
+	 * a different size can be specified with devtype_data->sfa_size.
+	 * The SFA1AD, SFA2AD, SFB1AD, and SFB2AD registers define the
+	 * top (end) of these four regions.
 	 */
-	qspi_writel(q, q->devtype_data->ahb_buf_size + addr_offset,
-		    base + QUADSPI_SFA1AD);
-	qspi_writel(q, q->devtype_data->ahb_buf_size * 2 + addr_offset,
-		    base + QUADSPI_SFA2AD);
-	qspi_writel(q, q->devtype_data->ahb_buf_size * 3 + addr_offset,
-		    base + QUADSPI_SFB1AD);
-	qspi_writel(q, q->devtype_data->ahb_buf_size * 4 + addr_offset,
-		    base + QUADSPI_SFB2AD);
+	sfa_size = q->devtype_data->sfa_size ? : q->devtype_data->ahb_buf_size;
+	qspi_writel(q, addr_offset + 1 * sfa_size, base + QUADSPI_SFA1AD);
+	qspi_writel(q, addr_offset + 2 * sfa_size, base + QUADSPI_SFA2AD);
+	qspi_writel(q, addr_offset + 3 * sfa_size, base + QUADSPI_SFB1AD);
+	qspi_writel(q, addr_offset + 4 * sfa_size, base + QUADSPI_SFB2AD);
 
 	q->selected = -1;
 
@@ -857,6 +884,8 @@ static void fsl_qspi_cleanup(void *data)
 {
 	struct fsl_qspi *q = data;
 
+	reset_control_assert(q->resets);
+
 	fsl_qspi_clk_disable_unprep(q);
 
 	mutex_destroy(&q->lock);
@@ -902,6 +931,10 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 	if (!q->ahb_addr)
 		return -ENOMEM;
 
+	q->resets = devm_reset_control_array_get_optional_exclusive(dev);
+	if (IS_ERR(q->resets))
+		return PTR_ERR(q->resets);
+
 	/* find the clocks */
 	q->clk_en = devm_clk_get(dev, "qspi_en");
 	if (IS_ERR(q->clk_en))
@@ -923,6 +956,10 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = reset_control_deassert(q->resets);
+	if (ret)
+		return ret;
+
 	/* find the irq */
 	ret = platform_get_irq(pdev, 0);
 	if (ret < 0)
@@ -976,6 +1013,7 @@ static const struct of_device_id fsl_qspi_dt_ids[] = {
 	{ .compatible = "fsl,imx6ul-qspi", .data = &imx6ul_data, },
 	{ .compatible = "fsl,ls1021a-qspi", .data = &ls1021a_data, },
 	{ .compatible = "fsl,ls2080a-qspi", .data = &ls2080a_data, },
+	{ .compatible = "spacemit,k1-qspi", .data = &spacemit_k1_data, },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_qspi_dt_ids);
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index bbf1fd4..b8b79bb 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -42,6 +42,7 @@ MODULE_PARM_DESC(polling_limit_us,
 		 "time in us to run a transfer in polling mode\n");
 
 #define MXC_RPM_TIMEOUT		2000 /* 2000ms */
+#define MXC_SPI_DEFAULT_SPEED	500000 /* 500KHz */
 
 #define MXC_CSPIRXDATA		0x00
 #define MXC_CSPITXDATA		0x04
@@ -424,8 +425,15 @@ static void spi_imx_buf_tx_swap(struct spi_imx_data *spi_imx)
 
 static void mx53_ecspi_rx_target(struct spi_imx_data *spi_imx)
 {
-	u32 val = ioread32be(spi_imx->base + MXC_CSPIRXDATA);
+	u32 val = readl(spi_imx->base + MXC_CSPIRXDATA);
+#ifdef __LITTLE_ENDIAN
+	unsigned int bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word);
 
+	if (bytes_per_word == 1)
+		swab32s(&val);
+	else if (bytes_per_word == 2)
+		swahw32s(&val);
+#endif
 	if (spi_imx->rx_buf) {
 		int n_bytes = spi_imx->target_burst % sizeof(val);
 
@@ -446,6 +454,9 @@ static void mx53_ecspi_tx_target(struct spi_imx_data *spi_imx)
 {
 	u32 val = 0;
 	int n_bytes = spi_imx->count % sizeof(val);
+#ifdef __LITTLE_ENDIAN
+	unsigned int bytes_per_word;
+#endif
 
 	if (!n_bytes)
 		n_bytes = sizeof(val);
@@ -458,7 +469,14 @@ static void mx53_ecspi_tx_target(struct spi_imx_data *spi_imx)
 
 	spi_imx->count -= n_bytes;
 
-	iowrite32be(val, spi_imx->base + MXC_CSPITXDATA);
+#ifdef __LITTLE_ENDIAN
+	bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word);
+	if (bytes_per_word == 1)
+		swab32s(&val);
+	else if (bytes_per_word == 2)
+		swahw32s(&val);
+#endif
+	writel(val, spi_imx->base + MXC_CSPITXDATA);
 }
 
 /* MX51 eCSPI */
@@ -591,7 +609,7 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx,
 	 * is not functional for imx53 Soc, config SPI burst completed when
 	 * BURST_LENGTH + 1 bits are received
 	 */
-	if (spi_imx->target_mode && is_imx53_ecspi(spi_imx))
+	if (spi_imx->target_mode)
 		cfg &= ~MX51_ECSPI_CONFIG_SBBCTRL(channel);
 	else
 		cfg |= MX51_ECSPI_CONFIG_SBBCTRL(channel);
@@ -679,7 +697,7 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
 
 	/* Clear BL field and set the right value */
 	ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
-	if (spi_imx->target_mode && is_imx53_ecspi(spi_imx))
+	if (spi_imx->target_mode)
 		ctrl |= (spi_imx->target_burst * 8 - 1)
 			<< MX51_ECSPI_CTRL_BL_OFFSET;
 	else {
@@ -690,8 +708,11 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
 	/* set clock speed */
 	ctrl &= ~(0xf << MX51_ECSPI_CTRL_POSTDIV_OFFSET |
 		  0xf << MX51_ECSPI_CTRL_PREDIV_OFFSET);
-	ctrl |= mx51_ecspi_clkdiv(spi_imx, spi_imx->spi_bus_clk, &clk);
-	spi_imx->spi_bus_clk = clk;
+
+	if (!spi_imx->target_mode) {
+		ctrl |= mx51_ecspi_clkdiv(spi_imx, spi_imx->spi_bus_clk, &clk);
+		spi_imx->spi_bus_clk = clk;
+	}
 
 	mx51_configure_cpha(spi_imx, spi);
 
@@ -1313,15 +1334,18 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 	if (!t)
 		return 0;
 
-	if (!t->speed_hz) {
-		if (!spi->max_speed_hz) {
-			dev_err(&spi->dev, "no speed_hz provided!\n");
-			return -EINVAL;
+	if (!spi_imx->target_mode) {
+		if (!t->speed_hz) {
+			if (!spi->max_speed_hz) {
+				dev_err(&spi->dev, "no speed_hz provided!\n");
+				return -EINVAL;
+			}
+			dev_dbg(&spi->dev, "using spi->max_speed_hz!\n");
+			spi_imx->spi_bus_clk = spi->max_speed_hz;
+		} else {
+			spi_imx->spi_bus_clk = t->speed_hz;
 		}
-		dev_dbg(&spi->dev, "using spi->max_speed_hz!\n");
-		spi_imx->spi_bus_clk = spi->max_speed_hz;
-	} else
-		spi_imx->spi_bus_clk = t->speed_hz;
+	}
 
 	spi_imx->bits_per_word = t->bits_per_word;
 	spi_imx->count = t->len;
@@ -1365,7 +1389,7 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 	spi_imx->rx_only = ((t->tx_buf == NULL)
 			|| (t->tx_buf == spi->controller->dummy_tx));
 
-	if (is_imx53_ecspi(spi_imx) && spi_imx->target_mode) {
+	if (spi_imx->target_mode) {
 		spi_imx->rx = mx53_ecspi_rx_target;
 		spi_imx->tx = mx53_ecspi_tx_target;
 		spi_imx->target_burst = t->len;
@@ -1641,8 +1665,7 @@ static int spi_imx_pio_transfer_target(struct spi_device *spi,
 	struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller);
 	int ret = 0;
 
-	if (is_imx53_ecspi(spi_imx) &&
-	    transfer->len > MX53_MAX_TRANSFER_BYTES) {
+	if (transfer->len > MX53_MAX_TRANSFER_BYTES) {
 		dev_err(&spi->dev, "Transaction too big, max size is %d bytes\n",
 			MX53_MAX_TRANSFER_BYTES);
 		return -EMSGSIZE;
@@ -1838,6 +1861,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 	controller->prepare_message = spi_imx_prepare_message;
 	controller->unprepare_message = spi_imx_unprepare_message;
 	controller->target_abort = spi_imx_target_abort;
+	spi_imx->spi_bus_clk = MXC_SPI_DEFAULT_SPEED;
 	controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_NO_CS |
 				SPI_MOSI_IDLE_LOW;
 
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 064b992..c8b2add 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -12,6 +12,9 @@
 #include <linux/spi/spi-mem.h>
 #include <linux/sched/task_stack.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/spi-mem.h>
+
 #include "internals.h"
 
 #define SPI_MEM_MAX_BUSWIDTH		8
@@ -403,7 +406,9 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		if (ret)
 			return ret;
 
+		trace_spi_mem_start_op(mem, op);
 		ret = ctlr->mem_ops->exec_op(mem, op);
+		trace_spi_mem_stop_op(mem, op);
 
 		spi_mem_access_end(mem);
 
diff --git a/drivers/spi/spi-microchip-core-spi.c b/drivers/spi/spi-microchip-core-spi.c
new file mode 100644
index 0000000..98bf0e6
--- /dev/null
+++ b/drivers/spi/spi-microchip-core-spi.c
@@ -0,0 +1,429 @@
+// SPDX-License-Identifier: (GPL-2.0)
+//
+// Microchip CoreSPI controller driver
+//
+// Copyright (c) 2025 Microchip Technology Inc. and its subsidiaries
+//
+// Author: Prajna Rajendra Kumar <prajna.rajendrakumar@microchip.com>
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+
+#define MCHP_CORESPI_MAX_CS				(8)
+#define MCHP_CORESPI_DEFAULT_FIFO_DEPTH			(4)
+#define MCHP_CORESPI_DEFAULT_MOTOROLA_MODE		(3)
+
+#define MCHP_CORESPI_CONTROL_ENABLE			BIT(0)
+#define MCHP_CORESPI_CONTROL_MASTER			BIT(1)
+#define MCHP_CORESPI_CONTROL_TX_DATA_INT		BIT(3)
+#define MCHP_CORESPI_CONTROL_RX_OVER_INT		BIT(4)
+#define MCHP_CORESPI_CONTROL_TX_UNDER_INT		BIT(5)
+#define MCHP_CORESPI_CONTROL_FRAMEURUN			BIT(6)
+#define MCHP_CORESPI_CONTROL_OENOFF			BIT(7)
+
+#define MCHP_CORESPI_STATUS_ACTIVE			BIT(7)
+#define MCHP_CORESPI_STATUS_SSEL			BIT(6)
+#define MCHP_CORESPI_STATUS_TXFIFO_UNDERFLOW		BIT(5)
+#define MCHP_CORESPI_STATUS_RXFIFO_FULL			BIT(4)
+#define MCHP_CORESPI_STATUS_TXFIFO_FULL			BIT(3)
+#define MCHP_CORESPI_STATUS_RXFIFO_EMPTY		BIT(2)
+#define MCHP_CORESPI_STATUS_DONE			BIT(1)
+#define MCHP_CORESPI_STATUS_FIRSTFRAME			BIT(0)
+
+#define MCHP_CORESPI_INT_TXDONE				BIT(0)
+#define MCHP_CORESPI_INT_RX_CHANNEL_OVERFLOW		BIT(2)
+#define MCHP_CORESPI_INT_TX_CHANNEL_UNDERRUN		BIT(3)
+#define MCHP_CORESPI_INT_CMDINT				BIT(4)
+#define MCHP_CORESPI_INT_SSEND				BIT(5)
+#define MCHP_CORESPI_INT_DATA_RX			BIT(6)
+#define MCHP_CORESPI_INT_TXRFM				BIT(7)
+
+#define MCHP_CORESPI_CONTROL2_INTEN_TXRFMT		BIT(7)
+#define MCHP_CORESPI_CONTROL2_INTEN_DATA_RX		BIT(6)
+#define MCHP_CORESPI_CONTROL2_INTEN_SSEND		BIT(5)
+#define MCHP_CORESPI_CONTROL2_INTEN_CMD			BIT(4)
+
+#define INT_ENABLE_MASK (MCHP_CORESPI_CONTROL_TX_DATA_INT | MCHP_CORESPI_CONTROL_RX_OVER_INT | \
+			 MCHP_CORESPI_CONTROL_TX_UNDER_INT)
+
+#define MCHP_CORESPI_REG_CONTROL			(0x00)
+#define MCHP_CORESPI_REG_INTCLEAR			(0x04)
+#define MCHP_CORESPI_REG_RXDATA				(0x08)
+#define MCHP_CORESPI_REG_TXDATA				(0x0c)
+#define MCHP_CORESPI_REG_INTMASK			(0X10)
+#define MCHP_CORESPI_REG_INTRAW				(0X14)
+#define MCHP_CORESPI_REG_CONTROL2			(0x18)
+#define MCHP_CORESPI_REG_COMMAND			(0x1c)
+#define MCHP_CORESPI_REG_STAT				(0x20)
+#define MCHP_CORESPI_REG_SSEL				(0x24)
+#define MCHP_CORESPI_REG_TXDATA_LAST			(0X28)
+#define MCHP_CORESPI_REG_CLK_DIV			(0x2c)
+
+struct mchp_corespi {
+	void __iomem *regs;
+	struct clk *clk;
+	const u8 *tx_buf;
+	u8 *rx_buf;
+	u32 clk_gen;
+	int irq;
+	unsigned int tx_len;
+	unsigned int rx_len;
+	u32 fifo_depth;
+};
+
+static inline void mchp_corespi_disable(struct mchp_corespi *spi)
+{
+	u8 control = readb(spi->regs + MCHP_CORESPI_REG_CONTROL);
+
+	control &= ~MCHP_CORESPI_CONTROL_ENABLE;
+
+	writeb(control, spi->regs + MCHP_CORESPI_REG_CONTROL);
+}
+
+static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi, u32 fifo_max)
+{
+	for (int i = 0; i < fifo_max; i++) {
+		u32 data;
+
+		while (readb(spi->regs + MCHP_CORESPI_REG_STAT) &
+		       MCHP_CORESPI_STATUS_RXFIFO_EMPTY)
+			;
+
+		/* On TX-only transfers always perform a dummy read */
+		data = readb(spi->regs + MCHP_CORESPI_REG_RXDATA);
+		if (spi->rx_buf)
+			*spi->rx_buf++ = data;
+
+		spi->rx_len--;
+	}
+}
+
+static void mchp_corespi_enable_ints(struct mchp_corespi *spi)
+{
+	u8 control = readb(spi->regs + MCHP_CORESPI_REG_CONTROL);
+
+	control |= INT_ENABLE_MASK;
+	writeb(control, spi->regs + MCHP_CORESPI_REG_CONTROL);
+}
+
+static void mchp_corespi_disable_ints(struct mchp_corespi *spi)
+{
+	u8 control = readb(spi->regs + MCHP_CORESPI_REG_CONTROL);
+
+	control &= ~INT_ENABLE_MASK;
+	writeb(control, spi->regs + MCHP_CORESPI_REG_CONTROL);
+}
+
+static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, u32 fifo_max)
+{
+	for (int i = 0; i < fifo_max; i++) {
+		if (readb(spi->regs + MCHP_CORESPI_REG_STAT) &
+		    MCHP_CORESPI_STATUS_TXFIFO_FULL)
+			break;
+
+		/* On RX-only transfers always perform a dummy write */
+		if (spi->tx_buf)
+			writeb(*spi->tx_buf++, spi->regs + MCHP_CORESPI_REG_TXDATA);
+		else
+			writeb(0xaa, spi->regs + MCHP_CORESPI_REG_TXDATA);
+
+		spi->tx_len--;
+	}
+}
+
+static void mchp_corespi_set_cs(struct spi_device *spi, bool disable)
+{
+	struct mchp_corespi *corespi = spi_controller_get_devdata(spi->controller);
+	u32 reg;
+
+	reg = readb(corespi->regs + MCHP_CORESPI_REG_SSEL);
+	reg &= ~BIT(spi_get_chipselect(spi, 0));
+	reg |= !disable << spi_get_chipselect(spi, 0);
+
+	writeb(reg, corespi->regs + MCHP_CORESPI_REG_SSEL);
+}
+
+static int mchp_corespi_setup(struct spi_device *spi)
+{
+	if (spi_get_csgpiod(spi, 0))
+		return 0;
+
+	if (spi->mode & (SPI_CS_HIGH)) {
+		dev_err(&spi->dev, "unable to support active-high CS in Motorola mode\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (spi->mode & SPI_MODE_X_MASK & ~spi->controller->mode_bits) {
+		dev_err(&spi->dev, "incompatible CPOL/CPHA, must match controller's Motorola mode\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *spi)
+{
+	u8 control = readb(spi->regs + MCHP_CORESPI_REG_CONTROL);
+
+	/* Master mode changes require core to be disabled.*/
+	control = (control & ~MCHP_CORESPI_CONTROL_ENABLE) | MCHP_CORESPI_CONTROL_MASTER;
+
+	writeb(control, spi->regs + MCHP_CORESPI_REG_CONTROL);
+
+	mchp_corespi_enable_ints(spi);
+
+	control = readb(spi->regs + MCHP_CORESPI_REG_CONTROL);
+	control |= MCHP_CORESPI_CONTROL_ENABLE;
+
+	writeb(control, spi->regs + MCHP_CORESPI_REG_CONTROL);
+}
+
+static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
+{
+	struct spi_controller *host = dev_id;
+	struct mchp_corespi *spi = spi_controller_get_devdata(host);
+	u8 intfield = readb(spi->regs + MCHP_CORESPI_REG_INTMASK) & 0xff;
+	bool finalise = false;
+
+	/* Interrupt line may be shared and not for us at all */
+	if (intfield == 0)
+		return IRQ_NONE;
+
+	if (intfield & MCHP_CORESPI_INT_TXDONE)
+		writeb(MCHP_CORESPI_INT_TXDONE, spi->regs + MCHP_CORESPI_REG_INTCLEAR);
+
+	if (intfield & MCHP_CORESPI_INT_RX_CHANNEL_OVERFLOW) {
+		writeb(MCHP_CORESPI_INT_RX_CHANNEL_OVERFLOW,
+		       spi->regs + MCHP_CORESPI_REG_INTCLEAR);
+		finalise = true;
+		dev_err(&host->dev,
+			"RX OVERFLOW: rxlen: %u, txlen: %u\n",
+			spi->rx_len, spi->tx_len);
+	}
+
+	if (intfield & MCHP_CORESPI_INT_TX_CHANNEL_UNDERRUN) {
+		writeb(MCHP_CORESPI_INT_TX_CHANNEL_UNDERRUN,
+		       spi->regs + MCHP_CORESPI_REG_INTCLEAR);
+		finalise = true;
+		dev_err(&host->dev,
+			"TX UNDERFLOW: rxlen: %u, txlen: %u\n",
+			spi->rx_len, spi->tx_len);
+	}
+
+	if (finalise)
+		spi_finalize_current_transfer(host);
+
+	return IRQ_HANDLED;
+}
+
+static int mchp_corespi_set_clk_div(struct mchp_corespi *spi,
+				    unsigned long target_hz)
+{
+	unsigned long pclk_hz, spi_hz;
+	u32 clk_div;
+
+	/* Get peripheral clock rate */
+	pclk_hz = clk_get_rate(spi->clk);
+	if (!pclk_hz)
+		return -EINVAL;
+
+	/*
+	 * Calculate clock rate generated by SPI master
+	 * Formula: SPICLK = PCLK / (2 * (CLK_DIV + 1))
+	 */
+	clk_div = DIV_ROUND_UP(pclk_hz, 2 * target_hz) - 1;
+
+	if (clk_div > 0xFF)
+		return -EINVAL;
+
+	spi_hz = pclk_hz / (2 * (clk_div + 1));
+
+	if (spi_hz > target_hz)
+		return -EINVAL;
+
+	writeb(clk_div, spi->regs + MCHP_CORESPI_REG_CLK_DIV);
+
+	return 0;
+}
+
+static int mchp_corespi_transfer_one(struct spi_controller *host,
+				     struct spi_device *spi_dev,
+				     struct spi_transfer *xfer)
+{
+	struct mchp_corespi *spi = spi_controller_get_devdata(host);
+	int ret;
+
+	ret = mchp_corespi_set_clk_div(spi, (unsigned long)xfer->speed_hz);
+	if (ret) {
+		dev_err(&host->dev, "failed to set clock divider for target %u Hz\n",
+			xfer->speed_hz);
+		return ret;
+	}
+
+	spi->tx_buf = xfer->tx_buf;
+	spi->rx_buf = xfer->rx_buf;
+	spi->tx_len = xfer->len;
+	spi->rx_len = xfer->len;
+
+	while (spi->tx_len) {
+		unsigned int fifo_max = min(spi->tx_len, spi->fifo_depth);
+
+		mchp_corespi_write_fifo(spi, fifo_max);
+		mchp_corespi_read_fifo(spi, fifo_max);
+	}
+
+	spi_finalize_current_transfer(host);
+	return 1;
+}
+
+static int mchp_corespi_probe(struct platform_device *pdev)
+{
+	const char *protocol = "motorola";
+	struct device *dev = &pdev->dev;
+	struct spi_controller *host;
+	struct mchp_corespi *spi;
+	struct resource *res;
+	u32 num_cs, mode, frame_size;
+	bool assert_ssel;
+	int ret = 0;
+
+	host = devm_spi_alloc_host(dev, sizeof(*spi));
+	if (!host)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, host);
+
+	if (of_property_read_u32(dev->of_node, "num-cs", &num_cs))
+		num_cs = MCHP_CORESPI_MAX_CS;
+
+	/*
+	 * Protocol: CFG_MODE
+	 * CoreSPI can be configured for Motorola, TI or NSC.
+	 * The current driver supports only Motorola mode.
+	 */
+	ret = of_property_read_string(dev->of_node, "microchip,protocol-configuration",
+				      &protocol);
+	if (ret && ret != -EINVAL)
+		return dev_err_probe(dev, ret, "Error reading protocol-configuration\n");
+	if (strcmp(protocol, "motorola") != 0)
+		return dev_err_probe(dev, -EINVAL,
+				     "CoreSPI: protocol '%s' not supported by this driver\n",
+				      protocol);
+
+	/*
+	 * Motorola mode (0-3): CFG_MOT_MODE
+	 * Mode is fixed in the IP configurator.
+	 */
+	ret = of_property_read_u32(dev->of_node, "microchip,motorola-mode", &mode);
+	if (ret)
+		mode = MCHP_CORESPI_DEFAULT_MOTOROLA_MODE;
+	else if (mode > 3)
+		return dev_err_probe(dev, -EINVAL,
+				     "invalid 'microchip,motorola-mode' value %u\n", mode);
+
+	/*
+	 * Frame size: CFG_FRAME_SIZE
+	 * The hardware allows frame sizes <= APB data width.
+	 * However, this driver currently only supports 8-bit frames.
+	 */
+	ret = of_property_read_u32(dev->of_node, "microchip,frame-size", &frame_size);
+	if (!ret && frame_size != 8)
+		return dev_err_probe(dev, -EINVAL,
+				     "CoreSPI: frame size %u not supported by this driver\n",
+				     frame_size);
+
+	/*
+	 * SSEL: CFG_MOT_SSEL
+	 * CoreSPI deasserts SSEL when the TX FIFO empties.
+	 * To prevent CS deassertion when TX FIFO drains, the ssel-active property
+	 * keeps CS asserted for the full SPI transfer.
+	 */
+	assert_ssel = of_property_read_bool(dev->of_node, "microchip,ssel-active");
+	if (!assert_ssel)
+		return dev_err_probe(dev, -EINVAL,
+				     "hardware must enable 'microchip,ssel-active' to keep CS asserted for the SPI transfer\n");
+
+	spi = spi_controller_get_devdata(host);
+
+	host->num_chipselect = num_cs;
+	host->mode_bits = mode;
+	host->setup = mchp_corespi_setup;
+	host->use_gpio_descriptors = true;
+	host->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
+	host->transfer_one = mchp_corespi_transfer_one;
+	host->set_cs = mchp_corespi_set_cs;
+	host->dev.of_node = dev->of_node;
+
+	ret = of_property_read_u32(dev->of_node, "fifo-depth", &spi->fifo_depth);
+	if (ret)
+		spi->fifo_depth = MCHP_CORESPI_DEFAULT_FIFO_DEPTH;
+
+	spi->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(spi->regs))
+		return PTR_ERR(spi->regs);
+
+	spi->irq = platform_get_irq(pdev, 0);
+	if (spi->irq < 0)
+		return spi->irq;
+
+	ret = devm_request_irq(dev, spi->irq, mchp_corespi_interrupt, IRQF_SHARED,
+			       dev_name(dev), host);
+	if (ret)
+		return dev_err_probe(dev, ret, "could not request irq\n");
+
+	spi->clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(spi->clk))
+		return dev_err_probe(dev, PTR_ERR(spi->clk), "could not get clk\n");
+
+	mchp_corespi_init(host, spi);
+
+	ret = devm_spi_register_controller(dev, host);
+	if (ret) {
+		mchp_corespi_disable(spi);
+		return dev_err_probe(dev, ret, "unable to register host for CoreSPI controller\n");
+	}
+
+	return 0;
+}
+
+static void mchp_corespi_remove(struct platform_device *pdev)
+{
+	struct spi_controller *host = platform_get_drvdata(pdev);
+	struct mchp_corespi *spi = spi_controller_get_devdata(host);
+
+	mchp_corespi_disable_ints(spi);
+	mchp_corespi_disable(spi);
+}
+
+/*
+ * Platform driver data structure
+ */
+
+#if defined(CONFIG_OF)
+static const struct of_device_id mchp_corespi_dt_ids[] = {
+	{ .compatible = "microchip,corespi-rtl-v5" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, mchp_corespi_dt_ids);
+#endif
+
+static struct platform_driver mchp_corespi_driver = {
+	.probe = mchp_corespi_probe,
+	.driver = {
+		.name = "microchip-corespi",
+		.of_match_table = of_match_ptr(mchp_corespi_dt_ids),
+	},
+	.remove = mchp_corespi_remove,
+};
+module_platform_driver(mchp_corespi_driver);
+MODULE_DESCRIPTION("Microchip CoreSPI controller driver");
+MODULE_AUTHOR("Prajna Rajendra Kumar <prajna.rajendrakumar@microchip.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-microchip-core.c b/drivers/spi/spi-mpfs.c
similarity index 71%
rename from drivers/spi/spi-microchip-core.c
rename to drivers/spi/spi-mpfs.c
index 9128b86..9a14d17 100644
--- a/drivers/spi/spi-microchip-core.c
+++ b/drivers/spi/spi-mpfs.c
@@ -99,7 +99,7 @@
 #define REG_CTRL2		(0x48)
 #define REG_FRAMESUP		(0x50)
 
-struct mchp_corespi {
+struct mpfs_spi {
 	void __iomem *regs;
 	struct clk *clk;
 	const u8 *tx_buf;
@@ -113,34 +113,34 @@ struct mchp_corespi {
 	int n_bytes;
 };
 
-static inline u32 mchp_corespi_read(struct mchp_corespi *spi, unsigned int reg)
+static inline u32 mpfs_spi_read(struct mpfs_spi *spi, unsigned int reg)
 {
 	return readl(spi->regs + reg);
 }
 
-static inline void mchp_corespi_write(struct mchp_corespi *spi, unsigned int reg, u32 val)
+static inline void mpfs_spi_write(struct mpfs_spi *spi, unsigned int reg, u32 val)
 {
 	writel(val, spi->regs + reg);
 }
 
-static inline void mchp_corespi_disable(struct mchp_corespi *spi)
+static inline void mpfs_spi_disable(struct mpfs_spi *spi)
 {
-	u32 control = mchp_corespi_read(spi, REG_CONTROL);
+	u32 control = mpfs_spi_read(spi, REG_CONTROL);
 
 	control &= ~CONTROL_ENABLE;
 
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 }
 
-static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi, int fifo_max)
+static inline void mpfs_spi_read_fifo(struct mpfs_spi *spi, int fifo_max)
 {
 	for (int i = 0; i < fifo_max; i++) {
 		u32 data;
 
-		while (mchp_corespi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY)
+		while (mpfs_spi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY)
 			;
 
-		data = mchp_corespi_read(spi, REG_RX_DATA);
+		data = mpfs_spi_read(spi, REG_RX_DATA);
 
 		spi->rx_len -= spi->n_bytes;
 
@@ -158,34 +158,34 @@ static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi, int fifo_max
 	}
 }
 
-static void mchp_corespi_enable_ints(struct mchp_corespi *spi)
+static void mpfs_spi_enable_ints(struct mpfs_spi *spi)
 {
-	u32 control = mchp_corespi_read(spi, REG_CONTROL);
+	u32 control = mpfs_spi_read(spi, REG_CONTROL);
 
 	control |= INT_ENABLE_MASK;
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 }
 
-static void mchp_corespi_disable_ints(struct mchp_corespi *spi)
+static void mpfs_spi_disable_ints(struct mpfs_spi *spi)
 {
-	u32 control = mchp_corespi_read(spi, REG_CONTROL);
+	u32 control = mpfs_spi_read(spi, REG_CONTROL);
 
 	control &= ~INT_ENABLE_MASK;
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 }
 
-static inline void mchp_corespi_set_xfer_size(struct mchp_corespi *spi, int len)
+static inline void mpfs_spi_set_xfer_size(struct mpfs_spi *spi, int len)
 {
 	u32 control;
 	u32 lenpart;
-	u32 frames = mchp_corespi_read(spi, REG_FRAMESUP);
+	u32 frames = mpfs_spi_read(spi, REG_FRAMESUP);
 
 	/*
 	 * Writing to FRAMECNT in REG_CONTROL will reset the frame count, taking
 	 * a shortcut requires an explicit clear.
 	 */
 	if (frames == len) {
-		mchp_corespi_write(spi, REG_COMMAND, COMMAND_CLRFRAMECNT);
+		mpfs_spi_write(spi, REG_COMMAND, COMMAND_CLRFRAMECNT);
 		return;
 	}
 
@@ -208,20 +208,20 @@ static inline void mchp_corespi_set_xfer_size(struct mchp_corespi *spi, int len)
 	 * that matches the documentation.
 	 */
 	lenpart = len & 0xffff;
-	control = mchp_corespi_read(spi, REG_CONTROL);
+	control = mpfs_spi_read(spi, REG_CONTROL);
 	control &= ~CONTROL_FRAMECNT_MASK;
 	control |= lenpart << CONTROL_FRAMECNT_SHIFT;
-	mchp_corespi_write(spi, REG_CONTROL, control);
-	mchp_corespi_write(spi, REG_FRAMESUP, len);
+	mpfs_spi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_FRAMESUP, len);
 }
 
-static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, int fifo_max)
+static inline void mpfs_spi_write_fifo(struct mpfs_spi *spi, int fifo_max)
 {
 	int i = 0;
 
-	mchp_corespi_set_xfer_size(spi, fifo_max);
+	mpfs_spi_set_xfer_size(spi, fifo_max);
 
-	while ((i < fifo_max) && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_TXFIFO_FULL)) {
+	while ((i < fifo_max) && !(mpfs_spi_read(spi, REG_STATUS) & STATUS_TXFIFO_FULL)) {
 		u32 word;
 
 		if (spi->n_bytes == 4)
@@ -231,7 +231,7 @@ static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, int fifo_ma
 		else
 			word = spi->tx_buf ? *spi->tx_buf : 0xaa;
 
-		mchp_corespi_write(spi, REG_TX_DATA, word);
+		mpfs_spi_write(spi, REG_TX_DATA, word);
 		if (spi->tx_buf)
 			spi->tx_buf += spi->n_bytes;
 		i++;
@@ -240,9 +240,9 @@ static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, int fifo_ma
 	spi->tx_len -= i * spi->n_bytes;
 }
 
-static inline void mchp_corespi_set_framesize(struct mchp_corespi *spi, int bt)
+static inline void mpfs_spi_set_framesize(struct mpfs_spi *spi, int bt)
 {
-	u32 frame_size = mchp_corespi_read(spi, REG_FRAME_SIZE);
+	u32 frame_size = mpfs_spi_read(spi, REG_FRAME_SIZE);
 	u32 control;
 
 	if ((frame_size & FRAME_SIZE_MASK) == bt)
@@ -252,25 +252,25 @@ static inline void mchp_corespi_set_framesize(struct mchp_corespi *spi, int bt)
 	 * Disable the SPI controller. Writes to the frame size have
 	 * no effect when the controller is enabled.
 	 */
-	control = mchp_corespi_read(spi, REG_CONTROL);
+	control = mpfs_spi_read(spi, REG_CONTROL);
 	control &= ~CONTROL_ENABLE;
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 
-	mchp_corespi_write(spi, REG_FRAME_SIZE, bt);
+	mpfs_spi_write(spi, REG_FRAME_SIZE, bt);
 
 	control |= CONTROL_ENABLE;
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 }
 
-static void mchp_corespi_set_cs(struct spi_device *spi, bool disable)
+static void mpfs_spi_set_cs(struct spi_device *spi, bool disable)
 {
 	u32 reg;
-	struct mchp_corespi *corespi = spi_controller_get_devdata(spi->controller);
+	struct mpfs_spi *mspi = spi_controller_get_devdata(spi->controller);
 
-	reg = mchp_corespi_read(corespi, REG_SLAVE_SELECT);
+	reg = mpfs_spi_read(mspi, REG_SLAVE_SELECT);
 	reg &= ~BIT(spi_get_chipselect(spi, 0));
 	reg |= !disable << spi_get_chipselect(spi, 0);
-	corespi->pending_slave_select = reg;
+	mspi->pending_slave_select = reg;
 
 	/*
 	 * Only deassert chip select immediately. Writing to some registers
@@ -281,12 +281,12 @@ static void mchp_corespi_set_cs(struct spi_device *spi, bool disable)
 	 * doesn't see any spurious clock transitions whilst CS is enabled.
 	 */
 	if (((spi->mode & SPI_CS_HIGH) == 0) == disable)
-		mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg);
+		mpfs_spi_write(mspi, REG_SLAVE_SELECT, reg);
 }
 
-static int mchp_corespi_setup(struct spi_device *spi)
+static int mpfs_spi_setup(struct spi_device *spi)
 {
-	struct mchp_corespi *corespi = spi_controller_get_devdata(spi->controller);
+	struct mpfs_spi *mspi = spi_controller_get_devdata(spi->controller);
 	u32 reg;
 
 	if (spi_is_csgpiod(spi))
@@ -298,21 +298,21 @@ static int mchp_corespi_setup(struct spi_device *spi)
 	 * driving their select line low.
 	 */
 	if (spi->mode & SPI_CS_HIGH) {
-		reg = mchp_corespi_read(corespi, REG_SLAVE_SELECT);
+		reg = mpfs_spi_read(mspi, REG_SLAVE_SELECT);
 		reg |= BIT(spi_get_chipselect(spi, 0));
-		corespi->pending_slave_select = reg;
-		mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg);
+		mspi->pending_slave_select = reg;
+		mpfs_spi_write(mspi, REG_SLAVE_SELECT, reg);
 	}
 	return 0;
 }
 
-static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *spi)
+static void mpfs_spi_init(struct spi_controller *host, struct mpfs_spi *spi)
 {
 	unsigned long clk_hz;
-	u32 control = mchp_corespi_read(spi, REG_CONTROL);
+	u32 control = mpfs_spi_read(spi, REG_CONTROL);
 
 	control &= ~CONTROL_ENABLE;
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 
 	control |= CONTROL_MASTER;
 	control &= ~CONTROL_MODE_MASK;
@@ -328,15 +328,15 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *
 	 */
 	control |= CONTROL_SPS | CONTROL_BIGFIFO;
 
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 
-	mchp_corespi_set_framesize(spi, DEFAULT_FRAMESIZE);
+	mpfs_spi_set_framesize(spi, DEFAULT_FRAMESIZE);
 
 	/* max. possible spi clock rate is the apb clock rate */
 	clk_hz = clk_get_rate(spi->clk);
 	host->max_speed_hz = clk_hz;
 
-	mchp_corespi_enable_ints(spi);
+	mpfs_spi_enable_ints(spi);
 
 	/*
 	 * It is required to enable direct mode, otherwise control over the chip
@@ -344,34 +344,34 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *
 	 * can deal with active high targets.
 	 */
 	spi->pending_slave_select = SSELOUT | SSEL_DIRECT;
-	mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
+	mpfs_spi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
 
-	control = mchp_corespi_read(spi, REG_CONTROL);
+	control = mpfs_spi_read(spi, REG_CONTROL);
 
 	control &= ~CONTROL_RESET;
 	control |= CONTROL_ENABLE;
 
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 }
 
-static inline void mchp_corespi_set_clk_gen(struct mchp_corespi *spi)
+static inline void mpfs_spi_set_clk_gen(struct mpfs_spi *spi)
 {
 	u32 control;
 
-	control = mchp_corespi_read(spi, REG_CONTROL);
+	control = mpfs_spi_read(spi, REG_CONTROL);
 	if (spi->clk_mode)
 		control |= CONTROL_CLKMODE;
 	else
 		control &= ~CONTROL_CLKMODE;
 
-	mchp_corespi_write(spi, REG_CLK_GEN, spi->clk_gen);
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CLK_GEN, spi->clk_gen);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 }
 
-static inline void mchp_corespi_set_mode(struct mchp_corespi *spi, unsigned int mode)
+static inline void mpfs_spi_set_mode(struct mpfs_spi *spi, unsigned int mode)
 {
 	u32 mode_val;
-	u32 control = mchp_corespi_read(spi, REG_CONTROL);
+	u32 control = mpfs_spi_read(spi, REG_CONTROL);
 
 	switch (mode & SPI_MODE_X_MASK) {
 	case SPI_MODE_0:
@@ -394,22 +394,22 @@ static inline void mchp_corespi_set_mode(struct mchp_corespi *spi, unsigned int 
 	 */
 
 	control &= ~CONTROL_ENABLE;
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 
 	control &= ~(SPI_MODE_X_MASK << MODE_X_MASK_SHIFT);
 	control |= mode_val;
 
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 
 	control |= CONTROL_ENABLE;
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mpfs_spi_write(spi, REG_CONTROL, control);
 }
 
-static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
+static irqreturn_t mpfs_spi_interrupt(int irq, void *dev_id)
 {
 	struct spi_controller *host = dev_id;
-	struct mchp_corespi *spi = spi_controller_get_devdata(host);
-	u32 intfield = mchp_corespi_read(spi, REG_MIS) & 0xf;
+	struct mpfs_spi *spi = spi_controller_get_devdata(host);
+	u32 intfield = mpfs_spi_read(spi, REG_MIS) & 0xf;
 	bool finalise = false;
 
 	/* Interrupt line may be shared and not for us at all */
@@ -417,7 +417,7 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	if (intfield & INT_RX_CHANNEL_OVERFLOW) {
-		mchp_corespi_write(spi, REG_INT_CLEAR, INT_RX_CHANNEL_OVERFLOW);
+		mpfs_spi_write(spi, REG_INT_CLEAR, INT_RX_CHANNEL_OVERFLOW);
 		finalise = true;
 		dev_err(&host->dev,
 			"%s: RX OVERFLOW: rxlen: %d, txlen: %d\n", __func__,
@@ -425,7 +425,7 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
 	}
 
 	if (intfield & INT_TX_CHANNEL_UNDERRUN) {
-		mchp_corespi_write(spi, REG_INT_CLEAR, INT_TX_CHANNEL_UNDERRUN);
+		mpfs_spi_write(spi, REG_INT_CLEAR, INT_TX_CHANNEL_UNDERRUN);
 		finalise = true;
 		dev_err(&host->dev,
 			"%s: TX UNDERFLOW: rxlen: %d, txlen: %d\n", __func__,
@@ -438,8 +438,8 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int mchp_corespi_calculate_clkgen(struct mchp_corespi *spi,
-					 unsigned long target_hz)
+static int mpfs_spi_calculate_clkgen(struct mpfs_spi *spi,
+				     unsigned long target_hz)
 {
 	unsigned long clk_hz, spi_hz, clk_gen;
 
@@ -475,20 +475,20 @@ static int mchp_corespi_calculate_clkgen(struct mchp_corespi *spi,
 	return 0;
 }
 
-static int mchp_corespi_transfer_one(struct spi_controller *host,
-				     struct spi_device *spi_dev,
-				     struct spi_transfer *xfer)
+static int mpfs_spi_transfer_one(struct spi_controller *host,
+				 struct spi_device *spi_dev,
+				 struct spi_transfer *xfer)
 {
-	struct mchp_corespi *spi = spi_controller_get_devdata(host);
+	struct mpfs_spi *spi = spi_controller_get_devdata(host);
 	int ret;
 
-	ret = mchp_corespi_calculate_clkgen(spi, (unsigned long)xfer->speed_hz);
+	ret = mpfs_spi_calculate_clkgen(spi, (unsigned long)xfer->speed_hz);
 	if (ret) {
 		dev_err(&host->dev, "failed to set clk_gen for target %u Hz\n", xfer->speed_hz);
 		return ret;
 	}
 
-	mchp_corespi_set_clk_gen(spi);
+	mpfs_spi_set_clk_gen(spi);
 
 	spi->tx_buf = xfer->tx_buf;
 	spi->rx_buf = xfer->rx_buf;
@@ -496,45 +496,46 @@ static int mchp_corespi_transfer_one(struct spi_controller *host,
 	spi->rx_len = xfer->len;
 	spi->n_bytes = roundup_pow_of_two(DIV_ROUND_UP(xfer->bits_per_word, BITS_PER_BYTE));
 
-	mchp_corespi_set_framesize(spi, xfer->bits_per_word);
+	mpfs_spi_set_framesize(spi, xfer->bits_per_word);
 
-	mchp_corespi_write(spi, REG_COMMAND, COMMAND_RXFIFORST | COMMAND_TXFIFORST);
+	mpfs_spi_write(spi, REG_COMMAND, COMMAND_RXFIFORST | COMMAND_TXFIFORST);
 
-	mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
+	mpfs_spi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
 
 	while (spi->tx_len) {
 		int fifo_max = DIV_ROUND_UP(min(spi->tx_len, FIFO_DEPTH), spi->n_bytes);
 
-		mchp_corespi_write_fifo(spi, fifo_max);
-		mchp_corespi_read_fifo(spi, fifo_max);
+		mpfs_spi_write_fifo(spi, fifo_max);
+		mpfs_spi_read_fifo(spi, fifo_max);
 	}
 
 	spi_finalize_current_transfer(host);
 	return 1;
 }
 
-static int mchp_corespi_prepare_message(struct spi_controller *host,
-					struct spi_message *msg)
+static int mpfs_spi_prepare_message(struct spi_controller *host,
+				    struct spi_message *msg)
 {
 	struct spi_device *spi_dev = msg->spi;
-	struct mchp_corespi *spi = spi_controller_get_devdata(host);
+	struct mpfs_spi *spi = spi_controller_get_devdata(host);
 
-	mchp_corespi_set_mode(spi, spi_dev->mode);
+	mpfs_spi_set_mode(spi, spi_dev->mode);
 
 	return 0;
 }
 
-static int mchp_corespi_probe(struct platform_device *pdev)
+static int mpfs_spi_probe(struct platform_device *pdev)
 {
 	struct spi_controller *host;
-	struct mchp_corespi *spi;
+	struct mpfs_spi *spi;
 	struct resource *res;
 	u32 num_cs;
 	int ret = 0;
 
 	host = devm_spi_alloc_host(&pdev->dev, sizeof(*spi));
 	if (!host)
-		return -ENOMEM;
+		return dev_err_probe(&pdev->dev, -ENOMEM,
+				     "unable to allocate host for SPI controller\n");
 
 	platform_set_drvdata(pdev, host);
 
@@ -544,11 +545,11 @@ static int mchp_corespi_probe(struct platform_device *pdev)
 	host->num_chipselect = num_cs;
 	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 	host->use_gpio_descriptors = true;
-	host->setup = mchp_corespi_setup;
+	host->setup = mpfs_spi_setup;
 	host->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
-	host->transfer_one = mchp_corespi_transfer_one;
-	host->prepare_message = mchp_corespi_prepare_message;
-	host->set_cs = mchp_corespi_set_cs;
+	host->transfer_one = mpfs_spi_transfer_one;
+	host->prepare_message = mpfs_spi_prepare_message;
+	host->set_cs = mpfs_spi_set_cs;
 	host->dev.of_node = pdev->dev.of_node;
 
 	spi = spi_controller_get_devdata(host);
@@ -561,7 +562,7 @@ static int mchp_corespi_probe(struct platform_device *pdev)
 	if (spi->irq < 0)
 		return spi->irq;
 
-	ret = devm_request_irq(&pdev->dev, spi->irq, mchp_corespi_interrupt,
+	ret = devm_request_irq(&pdev->dev, spi->irq, mpfs_spi_interrupt,
 			       IRQF_SHARED, dev_name(&pdev->dev), host);
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret,
@@ -572,11 +573,11 @@ static int mchp_corespi_probe(struct platform_device *pdev)
 		return dev_err_probe(&pdev->dev, PTR_ERR(spi->clk),
 				     "could not get clk\n");
 
-	mchp_corespi_init(host, spi);
+	mpfs_spi_init(host, spi);
 
 	ret = devm_spi_register_controller(&pdev->dev, host);
 	if (ret) {
-		mchp_corespi_disable(spi);
+		mpfs_spi_disable(spi);
 		return dev_err_probe(&pdev->dev, ret,
 				     "unable to register host for SPI controller\n");
 	}
@@ -586,13 +587,13 @@ static int mchp_corespi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void mchp_corespi_remove(struct platform_device *pdev)
+static void mpfs_spi_remove(struct platform_device *pdev)
 {
 	struct spi_controller *host  = platform_get_drvdata(pdev);
-	struct mchp_corespi *spi = spi_controller_get_devdata(host);
+	struct mpfs_spi *spi = spi_controller_get_devdata(host);
 
-	mchp_corespi_disable_ints(spi);
-	mchp_corespi_disable(spi);
+	mpfs_spi_disable_ints(spi);
+	mpfs_spi_disable(spi);
 }
 
 #define MICROCHIP_SPI_PM_OPS (NULL)
@@ -602,23 +603,23 @@ static void mchp_corespi_remove(struct platform_device *pdev)
  */
 
 #if defined(CONFIG_OF)
-static const struct of_device_id mchp_corespi_dt_ids[] = {
+static const struct of_device_id mpfs_spi_dt_ids[] = {
 	{ .compatible = "microchip,mpfs-spi" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, mchp_corespi_dt_ids);
+MODULE_DEVICE_TABLE(of, mpfs_spi_dt_ids);
 #endif
 
-static struct platform_driver mchp_corespi_driver = {
-	.probe = mchp_corespi_probe,
+static struct platform_driver mpfs_spi_driver = {
+	.probe = mpfs_spi_probe,
 	.driver = {
-		.name = "microchip-corespi",
+		.name = "microchip-spi",
 		.pm = MICROCHIP_SPI_PM_OPS,
-		.of_match_table = of_match_ptr(mchp_corespi_dt_ids),
+		.of_match_table = of_match_ptr(mpfs_spi_dt_ids),
 	},
-	.remove = mchp_corespi_remove,
+	.remove = mpfs_spi_remove,
 };
-module_platform_driver(mchp_corespi_driver);
+module_platform_driver(mpfs_spi_driver);
 MODULE_DESCRIPTION("Microchip coreSPI SPI controller driver");
 MODULE_AUTHOR("Daire McNamara <daire.mcnamara@microchip.com>");
 MODULE_AUTHOR("Conor Dooley <conor.dooley@microchip.com>");
diff --git a/drivers/spi/spi-offload-trigger-pwm.c b/drivers/spi/spi-offload-trigger-pwm.c
index 805ed41..3e8c192 100644
--- a/drivers/spi/spi-offload-trigger-pwm.c
+++ b/drivers/spi/spi-offload-trigger-pwm.c
@@ -51,12 +51,14 @@ static int spi_offload_trigger_pwm_validate(struct spi_offload_trigger *trigger,
 	wf.period_length_ns = DIV_ROUND_UP_ULL(NSEC_PER_SEC, periodic->frequency_hz);
 	/* REVISIT: 50% duty-cycle for now - may add config parameter later */
 	wf.duty_length_ns = wf.period_length_ns / 2;
+	wf.duty_offset_ns = periodic->offset_ns;
 
 	ret = pwm_round_waveform_might_sleep(st->pwm, &wf);
 	if (ret < 0)
 		return ret;
 
 	periodic->frequency_hz = DIV_ROUND_UP_ULL(NSEC_PER_SEC, wf.period_length_ns);
+	periodic->offset_ns = wf.duty_offset_ns;
 
 	return 0;
 }
@@ -77,6 +79,7 @@ static int spi_offload_trigger_pwm_enable(struct spi_offload_trigger *trigger,
 	wf.period_length_ns = DIV_ROUND_UP_ULL(NSEC_PER_SEC, periodic->frequency_hz);
 	/* REVISIT: 50% duty-cycle for now - may add config parameter later */
 	wf.duty_length_ns = wf.period_length_ns / 2;
+	wf.duty_offset_ns = periodic->offset_ns;
 
 	return pwm_set_waveform_might_sleep(st->pwm, &wf, false);
 }
diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 58ceea1..7681a91 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -448,7 +448,7 @@ static int qcom_spi_ecc_finish_io_req_pipelined(struct nand_device *nand,
 		return snandc->qspi->ecc_stats.bitflips;
 }
 
-static struct nand_ecc_engine_ops qcom_spi_ecc_engine_ops_pipelined = {
+static const struct nand_ecc_engine_ops qcom_spi_ecc_engine_ops_pipelined = {
 	.init_ctx = qcom_spi_ecc_init_ctx_pipelined,
 	.cleanup_ctx = qcom_spi_ecc_cleanup_ctx_pipelined,
 	.prepare_io_req = qcom_spi_ecc_prepare_io_req_pipelined,
diff --git a/drivers/spi/spi-rzv2h-rspi.c b/drivers/spi/spi-rzv2h-rspi.c
index dcc431b..1db7e4e 100644
--- a/drivers/spi/spi-rzv2h-rspi.c
+++ b/drivers/spi/spi-rzv2h-rspi.c
@@ -24,6 +24,7 @@
 /* Registers */
 #define RSPI_SPDR		0x00
 #define RSPI_SPCR		0x08
+#define RSPI_SPPCR		0x0e
 #define RSPI_SSLP		0x10
 #define RSPI_SPBR		0x11
 #define RSPI_SPSCR		0x13
@@ -34,13 +35,18 @@
 #define RSPI_SPFCR		0x6c
 
 /* Register SPCR */
+#define RSPI_SPCR_BPEN		BIT(31)
 #define RSPI_SPCR_MSTR		BIT(30)
 #define RSPI_SPCR_SPRIE		BIT(17)
 #define RSPI_SPCR_SCKASE	BIT(12)
 #define RSPI_SPCR_SPE		BIT(0)
 
+/* Register SPPCR */
+#define RSPI_SPPCR_SPLP2	BIT(1)
+
 /* Register SPBR */
 #define RSPI_SPBR_SPR_MIN	0
+#define RSPI_SPBR_SPR_PCLK_MIN	1
 #define RSPI_SPBR_SPR_MAX	255
 
 /* Register SPCMD */
@@ -58,7 +64,6 @@
 /* Register SPDCR2 */
 #define RSPI_SPDCR2_TTRG	GENMASK(11, 8)
 #define RSPI_SPDCR2_RTRG	GENMASK(3, 0)
-#define RSPI_FIFO_SIZE		16
 
 /* Register SPSR */
 #define RSPI_SPSR_SPRF		BIT(15)
@@ -67,17 +72,41 @@
 #define RSPI_SPSRC_CLEAR	0xfd80
 
 #define RSPI_RESET_NUM		2
-#define RSPI_CLK_NUM		3
+
+struct rzv2h_rspi_best_clock {
+	struct clk *clk;
+	unsigned long clk_rate;
+	unsigned long error;
+	u32 actual_hz;
+	u8 brdv;
+	u8 spr;
+};
+
+struct rzv2h_rspi_info {
+	void (*find_tclk_rate)(struct clk *clk, u32 hz, u8 spr_min, u8 spr_max,
+			       struct rzv2h_rspi_best_clock *best_clk);
+	void (*find_pclk_rate)(struct clk *clk, u32 hz, u8 spr_low, u8 spr_high,
+			       struct rzv2h_rspi_best_clock *best_clk);
+	const char *tclk_name;
+	unsigned int fifo_size;
+	unsigned int num_clks;
+};
 
 struct rzv2h_rspi_priv {
 	struct reset_control_bulk_data resets[RSPI_RESET_NUM];
 	struct spi_controller *controller;
+	const struct rzv2h_rspi_info *info;
 	void __iomem *base;
 	struct clk *tclk;
+	struct clk *pclk;
 	wait_queue_head_t wait;
 	unsigned int bytes_per_word;
+	u32 last_speed_hz;
 	u32 freq;
 	u16 status;
+	u8 spr;
+	u8 brdv;
+	bool use_pclk;
 };
 
 #define RZV2H_RSPI_TX(func, type)					\
@@ -232,9 +261,112 @@ static inline u32 rzv2h_rspi_calc_bitrate(unsigned long tclk_rate, u8 spr,
 	return DIV_ROUND_UP(tclk_rate, (2 * (spr + 1) * (1 << brdv)));
 }
 
-static u32 rzv2h_rspi_setup_clock(struct rzv2h_rspi_priv *rspi, u32 hz)
+static void rzv2h_rspi_find_rate_variable(struct clk *clk, u32 hz,
+					  u8 spr_min, u8 spr_max,
+					  struct rzv2h_rspi_best_clock *best)
+{
+	long clk_rate, clk_min_rate, clk_max_rate;
+	int min_rate_spr, max_rate_spr;
+	unsigned long error;
+	u32 actual_hz;
+	u8 brdv;
+	int spr;
+
+	/*
+	 * On T2H / N2H, the source for the SPI clock is PCLKSPIn, which is a
+	 * 1/32, 1/30, 1/25 or 1/24 divider of PLL4, which is 2400MHz,
+	 * resulting in either 75MHz, 80MHz, 96MHz or 100MHz.
+	 */
+	clk_min_rate = clk_round_rate(clk, 0);
+	if (clk_min_rate < 0)
+		return;
+
+	clk_max_rate = clk_round_rate(clk, ULONG_MAX);
+	if (clk_max_rate < 0)
+		return;
+
+	/*
+	 * From the manual:
+	 * Bit rate = f(PCLKSPIn) / (2 * (n + 1) * 2^N)
+	 *
+	 * If we adapt it to the current context, we get the following:
+	 * hz = rate / ((spr + 1) * (1 << (brdv + 1)))
+	 *
+	 * This can be written in multiple forms depending on what we want to
+	 * determine.
+	 *
+	 * To find the rate, having hz, spr and brdv:
+	 * rate = hz * (spr + 1) * (1 << (brdv + 1)
+	 *
+	 * To find the spr, having rate, hz, and spr:
+	 * spr = rate / (hz * (1 << (brdv + 1)) - 1
+	 */
+
+	for (brdv = RSPI_SPCMD_BRDV_MIN; brdv <= RSPI_SPCMD_BRDV_MAX; brdv++) {
+		/* Calculate the divisor needed to find the SPR from a rate. */
+		u32 rate_div = hz * (1 << (brdv + 1));
+
+		/*
+		 * If the SPR for the minimum rate is greater than the maximum
+		 * allowed value skip this BRDV. The divisor increases with each
+		 * BRDV iteration, so the following BRDV might result in a
+		 * minimum SPR that is in the valid range.
+		 */
+		min_rate_spr = DIV_ROUND_CLOSEST(clk_min_rate, rate_div) - 1;
+		if (min_rate_spr > spr_max)
+			continue;
+
+		/*
+		 * If the SPR for the maximum rate is less than the minimum
+		 * allowed value, exit. The divisor only increases with each
+		 * BRDV iteration, so the following BRDV cannot result in a
+		 * maximum SPR that is in the valid range.
+		 */
+		max_rate_spr = DIV_ROUND_CLOSEST(clk_max_rate, rate_div) - 1;
+		if (max_rate_spr < spr_min)
+			break;
+
+		if (min_rate_spr < spr_min)
+			min_rate_spr = spr_min;
+
+		if (max_rate_spr > spr_max)
+			max_rate_spr = spr_max;
+
+		for (spr = min_rate_spr; spr <= max_rate_spr; spr++) {
+			clk_rate = (spr + 1) * rate_div;
+
+			clk_rate = clk_round_rate(clk, clk_rate);
+			if (clk_rate <= 0)
+				continue;
+
+			actual_hz = rzv2h_rspi_calc_bitrate(clk_rate, spr, brdv);
+			error = abs((long)hz - (long)actual_hz);
+
+			if (error >= best->error)
+				continue;
+
+			*best = (struct rzv2h_rspi_best_clock) {
+				.clk = clk,
+				.clk_rate = clk_rate,
+				.error = error,
+				.actual_hz = actual_hz,
+				.brdv = brdv,
+				.spr = spr,
+			};
+
+			if (!error)
+				return;
+		}
+	}
+}
+
+static void rzv2h_rspi_find_rate_fixed(struct clk *clk, u32 hz,
+				       u8 spr_min, u8 spr_max,
+				       struct rzv2h_rspi_best_clock *best)
 {
-	unsigned long tclk_rate;
+	unsigned long clk_rate;
+	unsigned long error;
+	u32 actual_hz;
 	int spr;
 	u8 brdv;
 
@@ -247,21 +379,63 @@ static u32 rzv2h_rspi_setup_clock(struct rzv2h_rspi_priv *rspi, u32 hz)
 	 * * n = SPR - is RSPI_SPBR.SPR (from 0 to 255)
 	 * * N = BRDV - is RSPI_SPCMD.BRDV (from 0 to 3)
 	 */
-	tclk_rate = clk_get_rate(rspi->tclk);
+	clk_rate = clk_get_rate(clk);
 	for (brdv = RSPI_SPCMD_BRDV_MIN; brdv <= RSPI_SPCMD_BRDV_MAX; brdv++) {
-		spr = DIV_ROUND_UP(tclk_rate, hz * (1 << (brdv + 1)));
+		spr = DIV_ROUND_UP(clk_rate, hz * (1 << (brdv + 1)));
 		spr--;
-		if (spr >= RSPI_SPBR_SPR_MIN && spr <= RSPI_SPBR_SPR_MAX)
+		if (spr >= spr_min && spr <= spr_max)
 			goto clock_found;
 	}
 
-	return 0;
+	return;
 
 clock_found:
-	rzv2h_rspi_reg_rmw(rspi, RSPI_SPCMD, RSPI_SPCMD_BRDV, brdv);
-	writeb(spr, rspi->base + RSPI_SPBR);
+	actual_hz = rzv2h_rspi_calc_bitrate(clk_rate, spr, brdv);
+	error = abs((long)hz - (long)actual_hz);
+
+	if (error >= best->error)
+		return;
+
+	*best = (struct rzv2h_rspi_best_clock) {
+		.clk = clk,
+		.clk_rate = clk_rate,
+		.error = error,
+		.actual_hz = actual_hz,
+		.brdv = brdv,
+		.spr = spr,
+	};
+}
+
+static u32 rzv2h_rspi_setup_clock(struct rzv2h_rspi_priv *rspi, u32 hz)
+{
+	struct rzv2h_rspi_best_clock best_clock = {
+		.error = ULONG_MAX,
+	};
+	int ret;
+
+	rspi->info->find_tclk_rate(rspi->tclk, hz, RSPI_SPBR_SPR_MIN,
+				   RSPI_SPBR_SPR_MAX, &best_clock);
+
+	/*
+	 * T2H and N2H can also use PCLK as a source, which is 125MHz, but not
+	 * when both SPR and BRDV are 0.
+	 */
+	if (best_clock.error && rspi->info->find_pclk_rate)
+		rspi->info->find_pclk_rate(rspi->pclk, hz, RSPI_SPBR_SPR_PCLK_MIN,
+					   RSPI_SPBR_SPR_MAX, &best_clock);
+
+	if (!best_clock.clk_rate)
+		return -EINVAL;
 
-	return rzv2h_rspi_calc_bitrate(tclk_rate, spr, brdv);
+	ret = clk_set_rate(best_clock.clk, best_clock.clk_rate);
+	if (ret)
+		return 0;
+
+	rspi->use_pclk = best_clock.clk == rspi->pclk;
+	rspi->spr = best_clock.spr;
+	rspi->brdv = best_clock.brdv;
+
+	return best_clock.actual_hz;
 }
 
 static int rzv2h_rspi_prepare_message(struct spi_controller *ctlr,
@@ -274,10 +448,34 @@ static int rzv2h_rspi_prepare_message(struct spi_controller *ctlr,
 	u8 bits_per_word;
 	u32 conf32;
 	u16 conf16;
+	u8 conf8;
 
 	/* Make sure SPCR.SPE is 0 before amending the configuration */
 	rzv2h_rspi_spe_disable(rspi);
 
+	list_for_each_entry(xfer, &message->transfers, transfer_list) {
+		if (!xfer->speed_hz)
+			continue;
+
+		speed_hz = min(xfer->speed_hz, speed_hz);
+		bits_per_word = xfer->bits_per_word;
+	}
+
+	if (speed_hz == U32_MAX)
+		return -EINVAL;
+
+	rspi->bytes_per_word = roundup_pow_of_two(BITS_TO_BYTES(bits_per_word));
+
+	if (speed_hz != rspi->last_speed_hz) {
+		rspi->freq = rzv2h_rspi_setup_clock(rspi, speed_hz);
+		if (!rspi->freq)
+			return -EINVAL;
+
+		rspi->last_speed_hz = speed_hz;
+	}
+
+	writeb(rspi->spr, rspi->base + RSPI_SPBR);
+
 	/* Configure the device to work in "host" mode */
 	conf32 = RSPI_SPCR_MSTR;
 
@@ -287,15 +485,24 @@ static int rzv2h_rspi_prepare_message(struct spi_controller *ctlr,
 	/* SPI receive buffer full interrupt enable */
 	conf32 |= RSPI_SPCR_SPRIE;
 
+	/* Bypass synchronization circuit */
+	conf32 |= FIELD_PREP(RSPI_SPCR_BPEN, rspi->use_pclk);
+
 	writel(conf32, rspi->base + RSPI_SPCR);
 
 	/* Use SPCMD0 only */
 	writeb(0x0, rspi->base + RSPI_SPSCR);
 
+	/* Setup loopback */
+	conf8 = FIELD_PREP(RSPI_SPPCR_SPLP2, !!(spi->mode & SPI_LOOP));
+	writeb(conf8, rspi->base + RSPI_SPPCR);
+
 	/* Setup mode */
 	conf32 = FIELD_PREP(RSPI_SPCMD_CPOL, !!(spi->mode & SPI_CPOL));
 	conf32 |= FIELD_PREP(RSPI_SPCMD_CPHA, !!(spi->mode & SPI_CPHA));
 	conf32 |= FIELD_PREP(RSPI_SPCMD_LSBF, !!(spi->mode & SPI_LSB_FIRST));
+	conf32 |= FIELD_PREP(RSPI_SPCMD_SPB, bits_per_word - 1);
+	conf32 |= FIELD_PREP(RSPI_SPCMD_BRDV, rspi->brdv);
 	conf32 |= FIELD_PREP(RSPI_SPCMD_SSLKP, 1);
 	conf32 |= FIELD_PREP(RSPI_SPCMD_SSLA, spi_get_chipselect(spi, 0));
 	writel(conf32, rspi->base + RSPI_SPCMD);
@@ -305,30 +512,12 @@ static int rzv2h_rspi_prepare_message(struct spi_controller *ctlr,
 		writeb(0, rspi->base + RSPI_SSLP);
 
 	/* Setup FIFO thresholds */
-	conf16 = FIELD_PREP(RSPI_SPDCR2_TTRG, RSPI_FIFO_SIZE - 1);
+	conf16 = FIELD_PREP(RSPI_SPDCR2_TTRG, rspi->info->fifo_size - 1);
 	conf16 |= FIELD_PREP(RSPI_SPDCR2_RTRG, 0);
 	writew(conf16, rspi->base + RSPI_SPDCR2);
 
 	rzv2h_rspi_clear_fifos(rspi);
 
-	list_for_each_entry(xfer, &message->transfers, transfer_list) {
-		if (!xfer->speed_hz)
-			continue;
-
-		speed_hz = min(xfer->speed_hz, speed_hz);
-		bits_per_word = xfer->bits_per_word;
-	}
-
-	if (speed_hz == U32_MAX)
-		return -EINVAL;
-
-	rspi->bytes_per_word = roundup_pow_of_two(BITS_TO_BYTES(bits_per_word));
-	rzv2h_rspi_reg_rmw(rspi, RSPI_SPCMD, RSPI_SPCMD_SPB, bits_per_word - 1);
-
-	rspi->freq = rzv2h_rspi_setup_clock(rspi, speed_hz);
-	if (!rspi->freq)
-		return -EINVAL;
-
 	rzv2h_rspi_spe_enable(rspi);
 
 	return 0;
@@ -350,8 +539,8 @@ static int rzv2h_rspi_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct rzv2h_rspi_priv *rspi;
 	struct clk_bulk_data *clks;
-	unsigned long tclk_rate;
 	int irq_rx, ret, i;
+	long tclk_rate;
 
 	controller = devm_spi_alloc_host(dev, sizeof(*rspi));
 	if (!controller)
@@ -362,30 +551,32 @@ static int rzv2h_rspi_probe(struct platform_device *pdev)
 
 	rspi->controller = controller;
 
+	rspi->info = device_get_match_data(dev);
+
 	rspi->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(rspi->base))
 		return PTR_ERR(rspi->base);
 
 	ret = devm_clk_bulk_get_all_enabled(dev, &clks);
-	if (ret != RSPI_CLK_NUM)
+	if (ret != rspi->info->num_clks)
 		return dev_err_probe(dev, ret >= 0 ? -EINVAL : ret,
 				     "cannot get clocks\n");
-	for (i = 0; i < RSPI_CLK_NUM; i++) {
-		if (!strcmp(clks[i].id, "tclk")) {
+	for (i = 0; i < rspi->info->num_clks; i++) {
+		if (!strcmp(clks[i].id, rspi->info->tclk_name)) {
 			rspi->tclk = clks[i].clk;
-			break;
+		} else if (rspi->info->find_pclk_rate &&
+			   !strcmp(clks[i].id, "pclk")) {
+			rspi->pclk = clks[i].clk;
 		}
 	}
 
 	if (!rspi->tclk)
 		return dev_err_probe(dev, -EINVAL, "Failed to get tclk\n");
 
-	tclk_rate = clk_get_rate(rspi->tclk);
-
 	rspi->resets[0].id = "presetn";
 	rspi->resets[1].id = "tresetn";
-	ret = devm_reset_control_bulk_get_exclusive(dev, RSPI_RESET_NUM,
-						    rspi->resets);
+	ret = devm_reset_control_bulk_get_optional_exclusive(dev, RSPI_RESET_NUM,
+							     rspi->resets);
 	if (ret)
 		return dev_err_probe(dev, ret, "cannot get resets\n");
 
@@ -407,15 +598,29 @@ static int rzv2h_rspi_probe(struct platform_device *pdev)
 	}
 
 	controller->mode_bits = SPI_CPHA | SPI_CPOL | SPI_CS_HIGH |
-				SPI_LSB_FIRST;
+				SPI_LSB_FIRST | SPI_LOOP;
 	controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	controller->prepare_message = rzv2h_rspi_prepare_message;
 	controller->unprepare_message = rzv2h_rspi_unprepare_message;
 	controller->num_chipselect = 4;
 	controller->transfer_one = rzv2h_rspi_transfer_one;
+
+	tclk_rate = clk_round_rate(rspi->tclk, 0);
+	if (tclk_rate < 0) {
+		ret = tclk_rate;
+		goto quit_resets;
+	}
+
 	controller->min_speed_hz = rzv2h_rspi_calc_bitrate(tclk_rate,
 							   RSPI_SPBR_SPR_MAX,
 							   RSPI_SPCMD_BRDV_MAX);
+
+	tclk_rate = clk_round_rate(rspi->tclk, ULONG_MAX);
+	if (tclk_rate < 0) {
+		ret = tclk_rate;
+		goto quit_resets;
+	}
+
 	controller->max_speed_hz = rzv2h_rspi_calc_bitrate(tclk_rate,
 							   RSPI_SPBR_SPR_MIN,
 							   RSPI_SPCMD_BRDV_MIN);
@@ -445,8 +650,24 @@ static void rzv2h_rspi_remove(struct platform_device *pdev)
 	reset_control_bulk_assert(RSPI_RESET_NUM, rspi->resets);
 }
 
+static const struct rzv2h_rspi_info rzv2h_info = {
+	.find_tclk_rate = rzv2h_rspi_find_rate_fixed,
+	.tclk_name = "tclk",
+	.fifo_size = 16,
+	.num_clks = 3,
+};
+
+static const struct rzv2h_rspi_info rzt2h_info = {
+	.find_tclk_rate = rzv2h_rspi_find_rate_variable,
+	.find_pclk_rate = rzv2h_rspi_find_rate_fixed,
+	.tclk_name = "pclkspi",
+	.fifo_size = 4,
+	.num_clks = 2,
+};
+
 static const struct of_device_id rzv2h_rspi_match[] = {
-	{ .compatible = "renesas,r9a09g057-rspi" },
+	{ .compatible = "renesas,r9a09g057-rspi", &rzv2h_info },
+	{ .compatible = "renesas,r9a09g077-rspi", &rzt2h_info },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, rzv2h_rspi_match);
diff --git a/drivers/spi/spi-sg2044-nor.c b/drivers/spi/spi-sg2044-nor.c
index af48b1f..37f1cfe 100644
--- a/drivers/spi/spi-sg2044-nor.c
+++ b/drivers/spi/spi-sg2044-nor.c
@@ -42,6 +42,7 @@
 #define SPIFMC_TRAN_CSR_TRAN_MODE_RX		BIT(0)
 #define SPIFMC_TRAN_CSR_TRAN_MODE_TX		BIT(1)
 #define SPIFMC_TRAN_CSR_FAST_MODE		BIT(3)
+#define SPIFMC_TRAN_CSR_BUS_WIDTH_MASK		GENMASK(5, 4)
 #define SPIFMC_TRAN_CSR_BUS_WIDTH_1_BIT		(0x00 << 4)
 #define SPIFMC_TRAN_CSR_BUS_WIDTH_2_BIT		(0x01 << 4)
 #define SPIFMC_TRAN_CSR_BUS_WIDTH_4_BIT		(0x02 << 4)
@@ -122,8 +123,7 @@ static u32 sg2044_spifmc_init_reg(struct sg2044_spifmc *spifmc)
 	reg = readl(spifmc->io_base + SPIFMC_TRAN_CSR);
 	reg &= ~(SPIFMC_TRAN_CSR_TRAN_MODE_MASK |
 		 SPIFMC_TRAN_CSR_FAST_MODE |
-		 SPIFMC_TRAN_CSR_BUS_WIDTH_2_BIT |
-		 SPIFMC_TRAN_CSR_BUS_WIDTH_4_BIT |
+		 SPIFMC_TRAN_CSR_BUS_WIDTH_MASK |
 		 SPIFMC_TRAN_CSR_DMA_EN |
 		 SPIFMC_TRAN_CSR_ADDR_BYTES_MASK |
 		 SPIFMC_TRAN_CSR_WITH_CMD |
diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index 3be7499..cdc3cb7 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -1019,13 +1019,20 @@ static void tegra_qspi_dump_regs(struct tegra_qspi *tqspi)
 		tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS));
 }
 
+static void tegra_qspi_reset(struct tegra_qspi *tqspi)
+{
+	if (device_reset(tqspi->dev) < 0) {
+		dev_warn_once(tqspi->dev, "device reset failed\n");
+		tegra_qspi_mask_clear_irq(tqspi);
+	}
+}
+
 static void tegra_qspi_handle_error(struct tegra_qspi *tqspi)
 {
 	dev_err(tqspi->dev, "error in transfer, fifo status 0x%08x\n", tqspi->status_reg);
 	tegra_qspi_dump_regs(tqspi);
 	tegra_qspi_flush_fifos(tqspi, true);
-	if (device_reset(tqspi->dev) < 0)
-		dev_warn_once(tqspi->dev, "device reset failed\n");
+	tegra_qspi_reset(tqspi);
 }
 
 static void tegra_qspi_transfer_end(struct spi_device *spi)
@@ -1041,6 +1048,49 @@ static void tegra_qspi_transfer_end(struct spi_device *spi)
 	tegra_qspi_writel(tqspi, tqspi->def_command1_reg, QSPI_COMMAND1);
 }
 
+static irqreturn_t handle_cpu_based_xfer(struct tegra_qspi *tqspi);
+static irqreturn_t handle_dma_based_xfer(struct tegra_qspi *tqspi);
+
+/**
+ * tegra_qspi_handle_timeout - Handle transfer timeout with hardware check
+ * @tqspi: QSPI controller instance
+ *
+ * When a timeout occurs but hardware has completed the transfer (interrupt
+ * was lost or delayed), manually trigger transfer completion processing.
+ * This avoids failing transfers that actually succeeded.
+ *
+ * Returns: 0 if transfer was completed, -ETIMEDOUT if real timeout
+ */
+static int tegra_qspi_handle_timeout(struct tegra_qspi *tqspi)
+{
+	irqreturn_t ret;
+	u32 status;
+
+	/* Check if hardware actually completed the transfer */
+	status = tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS);
+	if (!(status & QSPI_RDY))
+		return -ETIMEDOUT;
+
+	/*
+	 * Hardware completed but interrupt was lost/delayed. Manually
+	 * process the completion by calling the appropriate handler.
+	 */
+	dev_warn_ratelimited(tqspi->dev,
+			     "QSPI interrupt timeout, but transfer complete\n");
+
+	/* Clear the transfer status */
+	status = tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS);
+	tegra_qspi_writel(tqspi, status, QSPI_TRANS_STATUS);
+
+	/* Manually trigger completion handler */
+	if (!tqspi->is_curr_dma_xfer)
+		ret = handle_cpu_based_xfer(tqspi);
+	else
+		ret = handle_dma_based_xfer(tqspi);
+
+	return (ret == IRQ_HANDLED) ? 0 : -EIO;
+}
+
 static u32 tegra_qspi_cmd_config(bool is_ddr, u8 bus_width, u8 len)
 {
 	u32 cmd_config = 0;
@@ -1072,6 +1122,30 @@ static u32 tegra_qspi_addr_config(bool is_ddr, u8 bus_width, u8 len)
 	return addr_config;
 }
 
+static void tegra_qspi_dma_stop(struct tegra_qspi *tqspi)
+{
+	u32 value;
+
+	if ((tqspi->cur_direction & DATA_DIR_TX) && tqspi->tx_dma_chan)
+		dmaengine_terminate_all(tqspi->tx_dma_chan);
+
+	if ((tqspi->cur_direction & DATA_DIR_RX) && tqspi->rx_dma_chan)
+		dmaengine_terminate_all(tqspi->rx_dma_chan);
+
+	value = tegra_qspi_readl(tqspi, QSPI_DMA_CTL);
+	value &= ~QSPI_DMA_EN;
+	tegra_qspi_writel(tqspi, value, QSPI_DMA_CTL);
+}
+
+static void tegra_qspi_pio_stop(struct tegra_qspi *tqspi)
+{
+	u32 value;
+
+	value = tegra_qspi_readl(tqspi, QSPI_COMMAND1);
+	value &= ~QSPI_PIO;
+	tegra_qspi_writel(tqspi, value, QSPI_COMMAND1);
+}
+
 static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 					struct spi_message *msg)
 {
@@ -1079,7 +1153,7 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 	struct spi_transfer *xfer;
 	struct spi_device *spi = msg->spi;
 	u8 transfer_phase = 0;
-	u32 cmd1 = 0, dma_ctl = 0;
+	u32 cmd1 = 0;
 	int ret = 0;
 	u32 address_value = 0;
 	u32 cmd_config = 0, addr_config = 0;
@@ -1146,41 +1220,28 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 					QSPI_DMA_TIMEOUT);
 
 			if (WARN_ON_ONCE(ret == 0)) {
-				dev_err_ratelimited(tqspi->dev,
-						    "QSPI Transfer failed with timeout\n");
-				if (tqspi->is_curr_dma_xfer) {
-					if ((tqspi->cur_direction & DATA_DIR_TX) &&
-					    tqspi->tx_dma_chan)
-						dmaengine_terminate_all(tqspi->tx_dma_chan);
-					if ((tqspi->cur_direction & DATA_DIR_RX) &&
-					    tqspi->rx_dma_chan)
-						dmaengine_terminate_all(tqspi->rx_dma_chan);
-				}
-
-				/* Abort transfer by resetting pio/dma bit */
-				if (!tqspi->is_curr_dma_xfer) {
-					cmd1 = tegra_qspi_readl
-							(tqspi,
-							 QSPI_COMMAND1);
-					cmd1 &= ~QSPI_PIO;
-					tegra_qspi_writel
-							(tqspi, cmd1,
-							 QSPI_COMMAND1);
-				} else {
-					dma_ctl = tegra_qspi_readl
-							(tqspi,
-							 QSPI_DMA_CTL);
-					dma_ctl &= ~QSPI_DMA_EN;
-					tegra_qspi_writel(tqspi, dma_ctl,
-							  QSPI_DMA_CTL);
+				/*
+				 * Check if hardware completed the transfer
+				 * even though interrupt was lost or delayed.
+				 * If so, process the completion and continue.
+				 */
+				ret = tegra_qspi_handle_timeout(tqspi);
+				if (ret < 0) {
+					/* Real timeout - clean up and fail */
+					dev_err(tqspi->dev, "transfer timeout\n");
+
+					/* Abort transfer by resetting pio/dma bit */
+					if (tqspi->is_curr_dma_xfer)
+						tegra_qspi_dma_stop(tqspi);
+					else
+						tegra_qspi_pio_stop(tqspi);
+
+					/* Reset controller if timeout happens */
+					tegra_qspi_reset(tqspi);
+
+					ret = -EIO;
+					goto exit;
 				}
-
-				/* Reset controller if timeout happens */
-				if (device_reset(tqspi->dev) < 0)
-					dev_warn_once(tqspi->dev,
-						      "device reset failed\n");
-				ret = -EIO;
-				goto exit;
 			}
 
 			if (tqspi->tx_status ||  tqspi->rx_status) {
@@ -1200,11 +1261,13 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 			tegra_qspi_transfer_end(spi);
 			spi_transfer_delay_exec(xfer);
 		}
+		tqspi->curr_xfer = NULL;
 		transfer_phase++;
 	}
 	ret = 0;
 
 exit:
+	tqspi->curr_xfer = NULL;
 	msg->status = ret;
 
 	return ret;
@@ -1269,16 +1332,23 @@ static int tegra_qspi_non_combined_seq_xfer(struct tegra_qspi *tqspi,
 		ret = wait_for_completion_timeout(&tqspi->xfer_completion,
 						  QSPI_DMA_TIMEOUT);
 		if (WARN_ON(ret == 0)) {
-			dev_err(tqspi->dev, "transfer timeout\n");
-			if (tqspi->is_curr_dma_xfer) {
-				if ((tqspi->cur_direction & DATA_DIR_TX) && tqspi->tx_dma_chan)
-					dmaengine_terminate_all(tqspi->tx_dma_chan);
-				if ((tqspi->cur_direction & DATA_DIR_RX) && tqspi->rx_dma_chan)
-					dmaengine_terminate_all(tqspi->rx_dma_chan);
+			/*
+			 * Check if hardware completed the transfer even though
+			 * interrupt was lost or delayed. If so, process the
+			 * completion and continue.
+			 */
+			ret = tegra_qspi_handle_timeout(tqspi);
+			if (ret < 0) {
+				/* Real timeout - clean up and fail */
+				dev_err(tqspi->dev, "transfer timeout\n");
+
+				if (tqspi->is_curr_dma_xfer)
+					tegra_qspi_dma_stop(tqspi);
+
+				tegra_qspi_handle_error(tqspi);
+				ret = -EIO;
+				goto complete_xfer;
 			}
-			tegra_qspi_handle_error(tqspi);
-			ret = -EIO;
-			goto complete_xfer;
 		}
 
 		if (tqspi->tx_status ||  tqspi->rx_status) {
@@ -1290,6 +1360,8 @@ static int tegra_qspi_non_combined_seq_xfer(struct tegra_qspi *tqspi,
 		msg->actual_length += xfer->len + dummy_bytes;
 
 complete_xfer:
+		tqspi->curr_xfer = NULL;
+
 		if (ret < 0) {
 			tegra_qspi_transfer_end(spi);
 			spi_transfer_delay_exec(xfer);
@@ -1395,6 +1467,7 @@ static irqreturn_t handle_cpu_based_xfer(struct tegra_qspi *tqspi)
 	tegra_qspi_calculate_curr_xfer_param(tqspi, t);
 	tegra_qspi_start_cpu_based_transfer(tqspi, t);
 exit:
+	tqspi->curr_xfer = NULL;
 	spin_unlock_irqrestore(&tqspi->lock, flags);
 	return IRQ_HANDLED;
 }
@@ -1480,6 +1553,15 @@ static irqreturn_t tegra_qspi_isr_thread(int irq, void *context_data)
 {
 	struct tegra_qspi *tqspi = context_data;
 
+	/*
+	 * Occasionally the IRQ thread takes a long time to wake up (usually
+	 * when the CPU that it's running on is excessively busy) and we have
+	 * already reached the timeout before and cleaned up the timed out
+	 * transfer. Avoid any processing in that case and bail out early.
+	 */
+	if (!tqspi->curr_xfer)
+		return IRQ_NONE;
+
 	tqspi->status_reg = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
 
 	if (tqspi->cur_direction & DATA_DIR_TX)
diff --git a/drivers/spi/spi-tle62x0.c b/drivers/spi/spi-tle62x0.c
index a565352..663c013 100644
--- a/drivers/spi/spi-tle62x0.c
+++ b/drivers/spi/spi-tle62x0.c
@@ -141,7 +141,7 @@ static ssize_t tle62x0_gpio_show(struct device *dev,
 	value = (st->gpio_state >> gpio_num) & 1;
 	mutex_unlock(&st->lock);
 
-	return sysfs_emit(buf, "%d", value);
+	return sysfs_emit(buf, "%d\n", value);
 }
 
 static ssize_t tle62x0_gpio_store(struct device *dev,
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 5300c94..9a0160f 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -704,6 +704,7 @@ static const struct class spidev_class = {
  */
 static const struct spi_device_id spidev_spi_ids[] = {
 	{ .name = /* abb */ "spi-sensor" },
+	{ .name = /* arduino */ "unoq-mcu" },
 	{ .name = /* cisco */ "spi-petra" },
 	{ .name = /* dh */ "dhcom-board" },
 	{ .name = /* elgin */ "jg10309-01" },
@@ -737,6 +738,7 @@ static int spidev_of_check(struct device *dev)
 
 static const struct of_device_id spidev_dt_ids[] = {
 	{ .compatible = "abb,spi-sensor", .data = &spidev_of_check },
+	{ .compatible = "arduino,unoq-mcu", .data = &spidev_of_check },
 	{ .compatible = "cisco,spi-petra", .data = &spidev_of_check },
 	{ .compatible = "dh,dhcom-board", .data = &spidev_of_check },
 	{ .compatible = "elgin,jg10309-01", .data = &spidev_of_check },
diff --git a/include/linux/platform_data/spi-davinci.h b/include/linux/platform_data/spi-davinci.h
deleted file mode 100644
index 2cb5cc7..0000000
--- a/include/linux/platform_data/spi-davinci.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright 2009 Texas Instruments.
- */
-
-#ifndef __ARCH_ARM_DAVINCI_SPI_H
-#define __ARCH_ARM_DAVINCI_SPI_H
-
-#include <linux/platform_data/edma.h>
-
-#define SPI_INTERN_CS	0xFF
-
-enum {
-	SPI_VERSION_1, /* For DM355/DM365/DM6467 */
-	SPI_VERSION_2, /* For DA8xx */
-};
-
-/**
- * davinci_spi_platform_data - Platform data for SPI master device on DaVinci
- *
- * @version:	version of the SPI IP. Different DaVinci devices have slightly
- *		varying versions of the same IP.
- * @num_chipselect: number of chipselects supported by this SPI master
- * @intr_line:	interrupt line used to connect the SPI IP to the ARM interrupt
- *		controller withn the SoC. Possible values are 0 and 1.
- * @cshold_bug:	set this to true if the SPI controller on your chip requires
- *		a write to CSHOLD bit in between transfers (like in DM355).
- * @dma_event_q: DMA event queue to use if SPI_IO_TYPE_DMA is used for any
- *		device on the bus.
- */
-struct davinci_spi_platform_data {
-	u8			version;
-	u8			num_chipselect;
-	u8			intr_line;
-	u8			prescaler_limit;
-	bool			cshold_bug;
-	enum dma_event_q	dma_event_q;
-};
-
-/**
- * davinci_spi_config - Per-chip-select configuration for SPI slave devices
- *
- * @wdelay:	amount of delay between transmissions. Measured in number of
- *		SPI module clocks.
- * @odd_parity:	polarity of parity flag at the end of transmit data stream.
- *		0 - odd parity, 1 - even parity.
- * @parity_enable: enable transmission of parity at end of each transmit
- *		data stream.
- * @io_type:	type of IO transfer. Choose between polled, interrupt and DMA.
- * @timer_disable: disable chip-select timers (setup and hold)
- * @c2tdelay:	chip-select setup time. Measured in number of SPI module clocks.
- * @t2cdelay:	chip-select hold time. Measured in number of SPI module clocks.
- * @t2edelay:	transmit data finished to SPI ENAn pin inactive time. Measured
- *		in number of SPI clocks.
- * @c2edelay:	chip-select active to SPI ENAn signal active time. Measured in
- *		number of SPI clocks.
- */
-struct davinci_spi_config {
-	u8	wdelay;
-	u8	odd_parity;
-	u8	parity_enable;
-#define SPI_IO_TYPE_INTR	0
-#define SPI_IO_TYPE_POLL	1
-#define SPI_IO_TYPE_DMA		2
-	u8	io_type;
-	u8	timer_disable;
-	u8	c2tdelay;
-	u8	t2cdelay;
-	u8	t2edelay;
-	u8	c2edelay;
-};
-
-#endif	/* __ARCH_ARM_DAVINCI_SPI_H */
diff --git a/include/linux/spi/offload/types.h b/include/linux/spi/offload/types.h
index 6f78923..cd61f8a 100644
--- a/include/linux/spi/offload/types.h
+++ b/include/linux/spi/offload/types.h
@@ -57,8 +57,17 @@ enum spi_offload_trigger_type {
 	SPI_OFFLOAD_TRIGGER_PERIODIC,
 };
 
+/**
+ * spi_offload_trigger_periodic - configuration parameters for periodic triggers
+ * @frequency_hz: The rate that the trigger should fire in Hz.
+ * @offset_ns: A delay in nanoseconds between when this trigger fires
+ *	       compared to another trigger. This requires specialized hardware
+ *	       that supports such synchronization with a delay between two or
+ *	       more triggers. Set to 0 when not needed.
+ */
 struct spi_offload_trigger_periodic {
 	u64 frequency_hz;
+	u64 offset_ns;
 };
 
 struct spi_offload_trigger_config {
diff --git a/include/trace/events/spi-mem.h b/include/trace/events/spi-mem.h
new file mode 100644
index 0000000..d13f0bc
--- /dev/null
+++ b/include/trace/events/spi-mem.h
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM spi-mem
+
+#undef TRACE_SYSTEM_VAR
+#define TRACE_SYSTEM_VAR spi_mem
+
+#if !defined(_TRACE_SPI_MEM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SPI_MEM_H
+
+#include <linux/tracepoint.h>
+#include <linux/spi/spi-mem.h>
+
+#define decode_dtr(dtr) \
+	__print_symbolic(dtr, \
+		{ 0, "S" }, \
+		{ 1, "D" })
+
+TRACE_EVENT(spi_mem_start_op,
+	TP_PROTO(struct spi_mem *mem, const struct spi_mem_op *op),
+	TP_ARGS(mem, op),
+
+	TP_STRUCT__entry(
+		__string(name, mem->name)
+		__dynamic_array(u8, op, 1 + op->addr.nbytes + op->dummy.nbytes)
+		__dynamic_array(u8, data, op->data.dir == SPI_MEM_DATA_OUT ?
+					  min(op->data.nbytes, 64) : 0)
+		__field(u32, data_len)
+		__field(u32, max_freq)
+		__field(u8, cmd_buswidth)
+		__field(bool, cmd_dtr)
+		__field(u8, addr_buswidth)
+		__field(bool, addr_dtr)
+		__field(u8, dummy_nbytes)
+		__field(u8, data_buswidth)
+		__field(bool, data_dtr)
+	),
+
+	TP_fast_assign(
+		int i;
+
+		__assign_str(name);
+		__entry->max_freq = op->max_freq ?: mem->spi->max_speed_hz;
+
+		__entry->cmd_buswidth = op->cmd.buswidth;
+		__entry->cmd_dtr = op->cmd.dtr;
+		*((u8 *)__get_dynamic_array(op)) = op->cmd.opcode;
+
+		__entry->addr_buswidth = op->addr.buswidth;
+		__entry->addr_dtr = op->addr.dtr;
+		for (i = 0; i < op->addr.nbytes; i++)
+			((u8 *)__get_dynamic_array(op))[i + 1] =
+				op->addr.val >> (8 * (op->addr.nbytes - i - 1));
+
+		memset(((u8 *)__get_dynamic_array(op)) + op->addr.nbytes + 1,
+		       0xff, op->dummy.nbytes);
+
+		__entry->data_len = op->data.nbytes;
+		__entry->data_buswidth = op->data.buswidth;
+		__entry->data_dtr = op->data.dtr;
+		if (op->data.dir == SPI_MEM_DATA_OUT)
+			memcpy(__get_dynamic_array(data), op->data.buf.out,
+			       __get_dynamic_array_len(data));
+	),
+
+	TP_printk("%s %u%s-%u%s-%u%s @%u Hz op=[%*phD] len=%u tx=[%*phD]",
+		__get_str(name),
+		__entry->cmd_buswidth, decode_dtr(__entry->cmd_dtr),
+		__entry->addr_buswidth, decode_dtr(__entry->addr_dtr),
+		__entry->data_buswidth, decode_dtr(__entry->data_dtr),
+		__entry->max_freq,
+		__get_dynamic_array_len(op), __get_dynamic_array(op),
+		__entry->data_len,
+		__get_dynamic_array_len(data), __get_dynamic_array(data))
+);
+
+TRACE_EVENT(spi_mem_stop_op,
+	TP_PROTO(struct spi_mem *mem, const struct spi_mem_op *op),
+	TP_ARGS(mem, op),
+
+	TP_STRUCT__entry(
+		__string(name, mem->name)
+		__dynamic_array(u8, data, op->data.dir == SPI_MEM_DATA_IN ?
+					  min(op->data.nbytes, 64) : 0)
+		__field(u32, data_len)
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		__entry->data_len = op->data.nbytes;
+		if (op->data.dir == SPI_MEM_DATA_IN)
+			memcpy(__get_dynamic_array(data), op->data.buf.in,
+			       __get_dynamic_array_len(data));
+	),
+
+	TP_printk("%s len=%u rx=[%*phD]",
+		__get_str(name),
+		__entry->data_len,
+		__get_dynamic_array_len(data), __get_dynamic_array(data))
+);
+
+
+#endif /* _TRACE_SPI_MEM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
